Sewing Machine and its Usage

Abstract

A method for calibrating one or more optical sensors on a sewing machine includes acquiring data of one or more features of one or more predefined regions associated with the sewing machine, processing the data through one or more neural networks, wherein the one or more neural networks detect and identify one or more features of the one or more predefined regions from the data, calculating one or more accuracy indices of the one or more features from the data compared with one or more training features from the one or more neural networks, comparing the values ​​of the one or more accuracy indices with one or more index thresholds, and adjusting one or more parameters of the one or more optical sensors based on the comparison between the one or more accuracy indices and the one or more index thresholds.

Description

[0001] Cross-reference to related applications

[0002] This application claims the benefit of U.S. Provisional Application No. 63 / 278,286, filed November 11, 2021, entitled “Sewing Machine and Method of Use Thereof” (Attorney’s Case No. 31982.04247), the entire contents of which are incorporated herein by reference. Technical Field

[0003] This invention relates generally to sewing machines, and more particularly to their control systems. Background Art

[0004] Sewing machines are used to form stitches on individual pieces of material and to sew pieces of material together. Specific sewing machines can be used to form stitches in workpieces with specific shapes, cut and sew along the edges of workpieces, attach decorative elements to workpieces, cut and sew along the edges of workpieces, attach decorative embroidery patterns to workpieces mounted in embroidery frames, or cut workpieces during sewing operations. Sewing machines can also cut, fold, roll, or otherwise manipulate workpieces, either separately from or outside of sewing programs. The workpiece moves beneath the needle to form stitches in the fabric. Users configure sewing machines for each specific application by adjusting various parameters and attaching a variety of different tools or accessories. Summary of the Invention

[0005] This document discloses exemplary embodiments of a sewing machine, its control system, and methods of using the machine.

[0006] An exemplary sewing machine includes a sewing head attached to an arm suspended above a sewing table by a support, a needle bar extending from the sewing head to the sewing table, a needle fixed to the needle bar, a motor connected to the needle bar for reciprocating movement of the needle bar during sewing operations to pass the needle and thread through the workpiece, and a user interface for receiving instructions from a user of the sewing machine and providing feedback to the user. The exemplary sewing machine also includes a data acquisition device, a data storage device, and a processor. The data acquisition device is used to acquire data related to at least one of the following: the sewing machine, the environment surrounding the sewing machine, the sewing material, the sewing operations performed by the sewing machine, and one or more interactions between the user and the sewing machine. The data storage device is used to store the data acquired by the data acquisition device as acquired data and to store data related to a neural network. The neural network consists of multiple nodes. Each node of the neural network has an input connection for receiving input data, node parameters, a computational unit for calculating an activation function based on the input data and node parameters, and an output connection for transmitting output data. The processor is configured to process the acquired data via a neural network to generate processed data, and based on the processed data, control at least one of a user interface for user interaction, a data storage device for storing the processed data, and a motor for changing the sewing operation.

[0007] An exemplary method for controlling a sewing machine includes the following steps: acquiring data, storing the acquired data in a data storage device, processing the acquired data via a neural network, and controlling a user interface, a data storage device, and a motor based on the processed data. The data acquisition step includes acquiring data related to at least one of the following: the sewing machine, the environment surrounding the sewing machine, the sewing material, the sewing operations performed by the sewing machine, and one or more interactions between the user and the sewing machine. The neural network in the processing step has multiple nodes, wherein each node includes an input connection for receiving input data, node parameters, a computational unit for calculating an activation function based on the input data and node parameters, and an output connection for transmitting output data. During the control step, the processor controls the user interface to interact with the user, controls the data storage device to store the processed data, and / or controls the motor to change the sewing operations.

[0008] An exemplary control system for a sewing machine includes a data acquisition device, a data storage device, and a processor. The data acquisition device is used to acquire data relating to at least one of the following: the sewing machine, the environment surrounding the sewing machine, the sewing material, the sewing operations performed by the sewing machine, and one or more interactions between the user and the sewing machine. The data storage device is used to store the data acquired by the data acquisition device as acquired data and to store data related to a neural network. The neural network consists of multiple nodes. Each node of the neural network has an input connection for receiving input data, node parameters, a computational unit for calculating an activation function based on the input data and node parameters, and an output connection for transmitting output data. The processor is configured to process the acquired data through the neural network to generate processed data, store the processed data in the data storage device, and control at least one of a user interface for user interaction and a motor for changing the sewing operations based on the processed data.

[0009] An exemplary method for calibrating one or more optical sensors on a sewing machine includes acquiring data of one or more features of one or more predefined regions associated with the sewing machine, processing the data through one or more neural networks, wherein the one or more neural networks detect and identify one or more features of the one or more predefined regions from the data, calculating one or more accuracy indices of the one or more features from the data compared with one or more training features from the one or more neural networks, comparing the values ​​of the one or more accuracy indices with one or more index thresholds, and adjusting one or more parameters of the one or more optical sensors based on the comparison between the one or more accuracy indices and the one or more index thresholds.

[0010] An exemplary sewing machine includes: a sewing head attached to an arm suspended above a sewing table by a support; a needle bar extending from the sewing head to the sewing table, wherein the needle bar holds a needle; a presser bar having a presser foot extending from the sewing head to the sewing table; one or more optical sensors arranged to acquire data from one or more features of one or more predefined regions associated with the sewing machine; and one or more processors configured to process the data acquired by the one or more optical sensors via one or more neural networks. The one or more processors are configured to receive data from the one or more optical sensors, process the data via one or more neural networks, wherein the one or more neural networks detect and identify one or more features of one or more predefined regions from the data, calculate one or more accuracy metrics for the one or more features from the data compared with training features from the one or more neural networks, compare the values ​​of the one or more accuracy metrics with one or more metric thresholds, and adjust one or more parameters of the one or more optical sensors based on the comparison between the one or more accuracy metrics and the one or more metric thresholds.

[0011] An exemplary sewing machine includes: a sewing head attached to an arm suspended above a sewing table by a support; a needle bar extending from the sewing head to the sewing table, wherein the needle bar holds a needle; a presser bar having a presser foot extending from the sewing head to the sewing table; one or more data acquisition devices associated with the sewing machine, arranged to acquire data from one or more features of one or more predefined regions associated with the sewing machine; and one or more processors configured to process the data acquired by the one or more data acquisition devices via one or more neural networks. The one or more processors are configured to receive data from the one or more data acquisition devices, process the data via one or more neural networks, wherein the one or more neural networks detect and identify one or more features of one or more predefined regions from the data, calculate one or more accuracy indices for the one or more features from the data compared with training features from the one or more neural networks, compare the values ​​of the one or more accuracy indices with one or more index thresholds, and adjust one or more parameters of the one or more data acquisition devices based on the comparison between the one or more accuracy indices and the one or more index thresholds.

[0012] A further understanding of the nature and advantages of the invention is set forth in the following description and claims, particularly when considered in conjunction with the accompanying drawings, in which like parts are given like reference numerals. Attached Figure Description

[0013] To further clarify various aspects of the embodiments of this disclosure, certain embodiments will be described in more detail with reference to various aspects of the accompanying drawings. It should be understood that these drawings depict only typical embodiments of this disclosure and should not be considered as limiting the scope of this disclosure. Furthermore, while the drawings may be drawn to scale for some embodiments, they are not necessarily drawn to scale for all embodiments. Embodiments and other features and advantages of this disclosure will be described and explained with additional specificity and detail using the accompanying drawings, wherein:

[0014] Figures 1 to 18 Various views and schematic diagrams related to an exemplary sewing machine and its system are shown;

[0015] Figures 19 to 23B The diagrams and flowcharts related to artificial intelligence and neural networks are shown.

[0016] Figures 24 to 33 Various views related to the stitch adjustment of an exemplary sewing machine are shown;

[0017] Figures 34 to 39 Schematic diagrams of various machine vision technologies are shown;

[0018] Figures 40 to 42Various views are shown in relation to exemplary sewing projection features of an exemplary sewing machine;

[0019] Figures 43 to 65 Various views related to the exemplary fabric and thread compatibility monitoring function of the exemplary sewing machine are shown;

[0020] Figures 66 to 70 Various views related to the exemplary thread quality monitoring features of an exemplary sewing machine are shown;

[0021] Figures 71 to 81 Various views related to exemplary object recognition features of an exemplary sewing machine are shown;

[0022] Figures 82 to 84 Various views are shown in relation to the exemplary haptic feedback features of an exemplary sewing machine; and

[0023] Figures 85 to 88 Various views related to exemplary machine diagnostic features of an exemplary sewing machine are shown;

[0024] Figure 89 A cross-sectional view of an exemplary line sensor is shown;

[0025] Figure 90 A perspective view of an exemplary sewing machine is shown;

[0026] Figure 91 It shows Figure 90 Front view of a sewing machine;

[0027] Figure 92 It shows Figure 90 A three-dimensional view of the lower left front of a sewing machine;

[0028] Figure 93 It shows Figure 90 A three-dimensional view of the lower left rear of a sewing machine;

[0029] Figure 94 It shows Figure 92 Detailed view of area 92 in the center;

[0030] Figure 95 It shows Figure 93 Detailed view of central area 93;

[0031] Figure 96 An exemplary process for controlling a sewing machine is shown; and

[0032] Figures 97 to 109 A flowchart detailing the operation of an exemplary sewing machine is shown. Detailed Implementation

[0033] The following description refers to the accompanying drawings, which illustrate specific embodiments of the present disclosure. Other embodiments with different structures and operations do not depart from the scope of this disclosure. Exemplary embodiments of the present disclosure relate to sewing machines and accessories used therewith.

[0034] As described herein, when one or more components are described as connected, joined, fixed, coupled, attached, or otherwise interconnected, such interconnection can be a direct interconnection between components or an indirect interconnection, for example, by using one or more intermediate components. Also as described herein, references to “component,” “assembly,” or “part” should not be limited to a single structural component, assembly, or element, but can include a collection of components, components, or elements. Also as described herein, the terms “substantially” and “approximately” are defined as at least close to (and including) a given value or state (preferably within 10%, more preferably within 1%, and most preferably within 0.1%).

[0035] Now refer to Figures 1 to 18 and Figures 90 to 95 Various views and schematic diagrams of an exemplary sewing machine and its parts are shown. An exemplary sewing machine, for example... Figure 1 The sewing machine 100 shown includes a sewing table or base 104 having a support 106 extending upward from one end to support an arm extending horizontally above the sewing table. A sewing head 102 is attached to the end of the arm and may include one or more needle bars 108 for moving one or more needles 110 up and down to sew a workpiece on the sewing table 104 below the sewing head 102. The sewing table includes a needle plate or seam plate arranged below the sewing head, having an opening for passing one or more needles 110 when making or forming stitches in the workpiece. In some sewing machines, a bobbin arranged below the needle plate helps form stitches and dispenses a lower thread that is sewn together with an upper thread fed from above through the workpiece by a needle. In other sewing machines, such as overlock or binding machines, the lower thread is dispensed by a looper. Users can interact with the sewing machine 100 through various buttons, knobs, switches, and other user interface elements. The touchscreen display 112 can also be used to present a software-based user interface to a user and receive input from the user. A projector 114 arranged in the sewing head 102 can be used to project one or more user interface elements onto the sewing table 104 or a workpiece placed thereon. One or more cameras 116 arranged in the sewing head 102 or elsewhere around the sewing machine 100 collect information from the workpiece and the surrounding environment of the sewing machine 100, which can be used to enhance the performance of the sewing machine 100 and the user experience.

[0036] As used herein, a "sewing machine" refers to a device that forms one or more stitches in a workpiece using a reciprocating needle and a length of thread. The term "sewing machine" as used herein includes, but is not limited to, sewing machines used to form specific stitches (e.g., sewing machines configured to form lockstitch, chain stitch, buttonhole stitch), embroidery machines, quilting machines, overlock machines, or binding machines. It should be noted that various embodiments of sewing machines and accessories are disclosed herein, and these options can be combined in any way unless specifically excluded. In other words, the various components or portions of the disclosed devices can be combined unless mutually exclusive or physically impossible.

[0037] A "stitch" is a loop of thread formed by one or more threads, wherein at least one thread passes through a hole formed in a workpiece. Mechanical components of a sewing machine, such as needles, hooks, loopers, thread tensioners, and feed mechanisms, cooperate to form stitches in one or more workpieces. A single repetition of this complex mechanical movement can form a stitch or a stitch pattern in a workpiece. The "stitch length" of a repetition or pattern refers to the distance the workpiece moves during the repetition. Stitch length measurement differs for different types of repetitions and patterns and may include one or more stitches in a workpiece.

[0038] A presser bar with a presser foot extends downwards from the sewing head to press the workpiece onto the sewing table and onto the feed dog, which moves from back to front and optionally left to right. The feed dog engages with the presser foot and moves the workpiece at a speed that can be fixed or variably controlled by the user (e.g., using a foot pedal). A variety of presser feet and other types of accessories can be attached to the presser bar to help form certain types of stitches or features in the workpiece, such as buttonhole presser feet. Accessory holders may also extend below the sewing head to hold special tools or accessories on or above the sewing table.

[0039] As mentioned above, the speed or frequency of the needle bar's up-and-down movement is controlled by the user. While the needle bar typically moves up and down in a cyclical motion to form stitches in the workpiece, it can also move left and right simultaneously to form different stitches, such as zigzag or tapered stitches, or to change the stitch width. Users can select the type and spacing of stitches executed by the sewing machine through a manual interface including buttons, knobs, joysticks, etc., a user interface presented on a computer touchscreen, or a voice control interface.

[0040] Different types of sewing machines may include additional components for forming stitches in a workpiece or otherwise manipulating the workpiece during the sewing process. For example, in an overlock machine (a type of sewing machine used to form the edge of a workpiece), among other functions, a needle called a looper runs below the sewing table to feed the thread used to form various stitches. Overlock machines may also include two, three, or more needles above the needle plate and a knife for cutting the edge of the workpiece. Sewing machines can also create embroidery patterns in a workpiece by including a support for an embroidery hoop on the sewing table (e.g., ...). Figure 6 The embroidery hoop support can be actuated on at least two axes, allowing the sewing machine's controller to move the embroidery frame so that the needle traces the embroidery pattern on the workpiece.

[0041] The thread used in the sewing process is fixed in different positions on the sewing machine, for example, inside the bobbin ( Figures 13 to 15 ) or on a spool held by a spool holder, which is part of the sewing machine arm or extends above the sewing machine arm ( Figures 10 to 12 The thread is drawn from a thread source (such as a bobbin or spool) and passes through various other elements of the sewing machine to one or more needles arranged to change the direction of the thread, thereby allowing it to be smoothly pulled out and fed to the workpiece with minimal damage to the thread. Figures 7 to 9 The tension of the thread can also be varied by various tensioning devices arranged along the thread path or within the thread source. Thread tensioning and dispensing devices ensure that only the desired amount of thread is dispensed, and that the thread forming the stitches in the workpiece is properly taut. Loose thread will cause the stitches to come loose, while tight thread will cause the stitches to form incorrectly. The thread tension on the upper and lower threads can also be adjusted to ensure that the tension is balanced from top to bottom so that the stitches are correctly formed along the desired sewing path in the workpiece.

[0042] Now refer to Figure 16This diagram illustrates a block diagram of a computer-based control system for a sewing machine 100. The sewing machine includes one or more data acquisition devices 118, one or more data storage devices 120, a processor 122, a user interface 124, and motors and actuators 126. The sewing machine 100 may also include a network interface connected to the processor 122 for connecting the sewing machine 100 to a cloud system and / or other sewing machines or devices via a wireless network. The data acquisition devices 118 include a variety of digital sensors, analog sensors, active sensors, passive sensors, and software components, as described in more detail below. These sensors acquire data related to the sewing machine itself, the workspace or environment surrounding the sewing machine, the sewing operations performed by the sewing machine, user interactions with the sewing machine, and the sewing materials (e.g., fabrics and threads) manipulated by the sewing machine. The data storage devices 120 include one or more computer memory chips for storing data acquired by the data acquisition devices 118 and the operating software of the sewing machine 100. The structure, various functions, and parameters of one or more neural networks 128 are also stored in the data storage devices 120. Processor 122 accesses data stored on data storage device 120 and executes operating software to enable the sewing machine 100 to function. User interface 124 is presented to the user via touchscreen display 112 and physical controls (e.g., buttons, joysticks, dials, lights, speakers, actuators, etc.). Motors and actuators 126 include electromechanical actuators, motors, and general mechanical components controlled by the control system to cause movement of various moving parts of the sewing machine (i.e., needle bar, feed dog, bobbin, looper, etc.). For example, the speed of the motor can be directly controlled by input from a user-actuated foot pedal, or it can be controlled by a computer that receives and interprets the foot pedal input before transmitting signals to one or more motor controllers that control the motors of the sewing machine.

[0043] The term "computer" or "processor" as used herein includes, but is not limited to, any programmable or programmable electronic device or coordinating device capable of storing, retrieving, and processing data, and can be a processing unit or a distributed processing configuration. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs), floating-point units (FPUs), reduced instruction set computing (RISC) processors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), and the like. One or more cores of a single microprocessor and / or multiple microprocessors, each having one or more cores, can be used to perform the operations described herein performed by the processor. The processor can also be a processor dedicated to training neural networks and other artificial intelligence (AI) systems. One or more processors can be locally mounted on a sewing machine and can be located at a remote location accessible via a network interface.

[0044] The terms "network interface" or "data interface" as used herein include, but are not limited to, any interface or protocol used for transmitting and receiving data between electronic devices. A network or data interface can refer to a connection to a computer via a local network or the Internet, or a connection via a wired or wireless connection to a portable device (such as a mobile device or a USB thumb drive). A network interface can be used to form a network of computers to facilitate distributed and / or remote computing (i.e., cloud-based computing). "Cloud-based computing" refers to computing implemented on a network of computing devices remotely connected to the sewing machine via a network interface.

[0045] As used herein, “logic” is synonymous with “circuit” and includes, but is not limited to, hardware, firmware, software, and / or combinations thereof for performing one or more functions or actions. For example, depending on the desired application or requirement, logic may include a software-controlled processor, discrete logic such as an application-specific integrated circuit (ASIC), a programmable logic device, or other processor. Logic may also be entirely embodied as software. “Software” as used herein includes, but is not limited to, one or more computer-readable and / or executable instructions that cause a processor or other electronic device to perform functions, actions, processes, and / or behaviors in a desired manner. Instructions may be embodied in various forms, such as routines, algorithms, modules, or programs, including standalone applications or code from dynamic link libraries (DLLs). Software may also be implemented in various forms, such as standalone programs, web-based programs, function calls, subroutines, servlets, application software, applications, applets (e.g., Java applets), plug-ins, instructions stored in memory, part of an operating system, or other types of executable or interpreted instructions from which executable instructions are created.

[0046] As used herein, "data storage device" means one or more devices for the non-transitory storage of code or data, such as devices having a non-transitory computer-readable medium. As used herein, "non-transitory computer-readable medium" means any suitable non-transitory computer-readable medium for storing code or data, such as magnetic media, such as a fixed disk in an external hard disk drive, a fixed disk in an internal hard disk drive, and a floppy disk; optical media, such as CDs, DVDs, and other media, such as read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), flash PROM, external flash drive, etc.

[0047] The user interface of a sewing machine can include various input devices and methods of communication with the user, such as buttons, knobs, switches, lights, displays, speakers, touch interfaces, and lamps. The sewing machine's user interface can be graphically presented to the user through one or more displays, including a touchscreen display 112 that includes a touch-sensitive overlay for detecting the position of the user's finger on the touchscreen. Therefore, the user can directly touch the screen at a specific location using their hand 150 and perform touch gestures (such as...). Figure 2 The touch gestures shown (152, 152 and hold, 156, 152 and collapse or expand, and 158) allow interaction with the user interface. Interaction can also be achieved through gestures from optical sensors (e.g., cameras) or proximity sensors (e.g., [missing information]). Figure 3 The data analysis detects the presence, position, and movement of the user's hand, fingers, or eyes through perturbations of sound, light, infrared radiation, or electromagnetic fields. The graphical user interface can also be projected onto the sewing table 104, the workpiece, an adjacent surface such as a wall or table, or any other suitable surface by one or more projectors of the sewing machine. Alternatively, the sewing machine 100 can be operated without a graphical user interface via voice commands and auditory feedback in the form of some sound and / or computerized speech. Tactile feedback can also be provided by actuators, which vibrate various parts of the machine (e.g., feedback section 160) in response to various conditions of the workpiece, the machine, etc. Auditory and tactile interaction with the sewing machine is particularly useful for visually impaired users.

[0048] like Figure 17 As shown, the sewing machine 100 can provide notifications and feedback to the user through visual, auditory, and tactile means. For example, an indication that an incorrect accessory is installed on the machine can be displayed to the user via the user interface on the sewing machine's display, while a notification sound, such as a beep or computerized sound, is sent to the user via a speaker in the sewing machine. This notification can also be sent to the user via tactile feedback through vibration of the feedback section 160 of the sewing machine 100 touched by the user. That is, the sewing machine can vibrate the sewing table 104 to provide a warning to the user that the machine is not correctly configured for a specific sewing operation selected by the user. The user will feel the vibration under their fingers in contact with the workpiece and the sewing table, prompting them to check the display for more information. The sewing machine's lights can also be controlled to alert the user, for example, by changing the flashing color when an incorrect accessory is installed, thus prompting the user to check the display for additional information.

[0049] like Figure 1 , Figure 4 , Figure 92 and Figure 94As shown, a projector 114 can also be installed in the sewing head 102, pointing downwards towards the sewing table 104 and the workpiece. The projector 114 is arranged to project useful information onto the workpiece to assist the user in using the sewing machine. For example, the projector 114 can project the needle drop point downwards onto the fabric, allowing the user to see the needle's position before making a stitch. Thread or other guides can also be projected onto the workpiece to help the user sew along a straight line or a desired path. Similar to guides, the projector 114 can project a selected stitch pattern onto the workpiece to indicate the planned stitch. The projector 114 is also capable of projecting images onto the workpiece to display the selected embroidery pattern, allowing the user to position the embroidery pattern at the desired location on the workpiece. The information projected by the projector 114 can also include feedback to the user regarding the machine's status or a specific sewing operation. For example, the projector 114 can project a warning notification onto the workpiece indicating that an incorrect needle has been installed for the type of material used as the workpiece. Projector 114 can also provide visual instructions to assist the user, such as static or animated images instructing the user on how to change needles, thread the machine, or rotate the workpiece. In other words, projector 114 can be used by a computer as another means of providing feedback and instructions to the user. It should also be noted that the images projected by projector 114 can also be detected by optical sensors, allowing the sewing machine to respond to user interaction with these images, such as by touching a button or a series of buttons projecting the image.

[0050] The sewing machine 100 can use a variety of data acquisition devices 118, namely digital sensors, analog sensors, active sensors, passive sensors, and software components, all of which can be used by the sewing machine 100 to acquire data related to the sewing machine itself, the workspace or environment around the sewing machine, the sewing materials operated by the sewing machine (e.g., fabric workpieces and threads used to form stitches), the sewing operations performed by the sewing machine, and the user's interaction with the sewing machine. A non-exhaustive list of sensor types for the sewing machine 100 includes: acoustic, sound, vibration, chemical, biometric, sweat, respiration, fatigue detection, gas, smoke, retina, fingerprint, fluid velocity, speed, temperature, optical (e.g., camera), light, infrared, ambient light level, color, red-green-blue (RGB) color (or other color space sensors, such as sensors using four-color printing (CMYK) or grayscale color space), touch, tilt, motion, metal detector, magnetic field, humidity, moisture, imaging, photons, pressure, force, density, proximity, ultrasound, load cell, digital accelerometer, motion, translation, friction, compressibility, sound, microphone, voltage, current, impedance, barometer, gyroscope, Hall effect, magnetometer, GPS, resistance, tension, strain, etc. The software-based data acquisition device 118 may include various data logs entered during the use of the sewing machine 100. For example, the user activity log may record events involving input from the user via the user interface 124, and the system event log may record software events that occur during normal use of the sewing machine 100 and can be used for machine learning or diagnostic purposes.

[0051] The sensors can be placed in various locations on the machine and can be used by the sewing machine in various ways. For example, the sewing machine may include touch and proximity sensors 170 (e.g. Figure 3 The proximity sensor 170 shown is used to provide touch control of the user interface displayed on the sewing machine's monitor. Similar touch or proximity sensors may also be located in other locations on the sewing machine, such as the arm or sewing table. These other touch sensors may be used in conjunction with the user interface presented to the user, or for safety purposes during sewing, to monitor the position of the user's hand (or other foreign objects, such as the user's hair or a loose sewing needle) on the machine. The sewing machine may also include eye-tracking sensors, including optical sensors, such as cameras or other detection means, for tracking the user's eye position and / or line of sight. One or more optical sensors on the machine may be used not only to collect user-related data about the machine, but also to collect data related to the workpiece, other sewing materials (such as thread), and the sewing machine itself. Additional examples of the use of sensors and sensor data through sewing are provided throughout this disclosure.

[0052] Many sensors used in sewing machines require calibration after installation to ensure the accuracy of the data acquired by the sensors and fed to the neural network. Sensor calibration can also be performed periodically in the field or when specified by the user. Sensors can be calibrated in any suitable manner. For example, camera calibration can be performed using the technique described in U.S. Patent No. 8,606,390, which is incorporated herein by reference. Cameras and other sensors can also be calibrated using techniques employing neural networks, such as identifying features of the sewing machine while calibrating a camera.

[0053] One or more optical sensors of a sewing machine can be arranged in various locations around the sewing machine. As used herein, "optical sensor" refers to a sensor capable of acquiring data from electromagnetic radiation (see...). Figure 18 This includes, but is not limited to, sensors for detecting ultraviolet, visible, and infrared radiation. Some optical sensors can be tuned to electromagnetic radiation of a specific wavelength, such as laser light of a specific wavelength. One particular optical sensor that can be used in an exemplary sewing machine is a camera. The camera may include lenses for focusing or otherwise redirecting light onto a sensor that receives optical data and transmits optical data to another device for processing.

[0054] One or more optical sensors can be placed in the sewing machine to observe the workpiece during the sewing process, such as in... Figure 1 , 4 Camera 116, as shown in 6, 93, and 95, can be used to determine the workpiece's color, material, position, orientation, range of motion, and direction using one or more optical sensors that observe the workpiece. The same optical sensors can also be used to detect objects in the sewing area, such as the user's hand, hazardous objects (e.g., the user's hair, clothing, sewing needles, etc.), the type of one or more needles installed in the sewing machine, the type of presser foot, etc. Optical sensors can also monitor whether needles, presser feet, needle plates, or accessories are correctly installed and maintain this correct installation during use. Additional optical sensors or similar sensing devices can be arranged on the user-facing machine to provide the sewing machine's computer with information about the user, such as the position and gaze of the user's eyes, so that the sewing machine can determine where the user is looking at the machine. For example, tracking the user's eyes and current gaze can allow the sewing machine to determine the optimal position for illuminating the sewing table or to provide the user with useful information so that important notifications or warnings are not missed.

[0055] Various security features can be included in sewing machines to restrict access and prevent theft. For example, when the machine is powered on or awakened from sleep mode, a prompt requiring the user to verify their identity can be displayed. The user can then enter a pre-defined code to prove they are authorized to access and use the sewing machine. In addition to or instead of a pre-defined code, the user can provide biometric information as identification, such as a fingerprint sensor or facial recognition. A fingerprint sensor can be included on the sewing table or in another location where the user typically places their hand to use the machine. One or more user-facing cameras enable the sewing machine to use facial recognition technology to identify the user and grant access to the machine.

[0056] Users can also associate another device with their account on the sewing machine and use that device to unlock the machine. For example, an app on a smartphone or tablet can be associated with the user's account, allowing the machine to be unlocked via the app or by keeping the smartphone or laptop within a predetermined range of the sewing machine. Any of these methods of authenticating users can be used individually or together to provide two-factor authentication. A phone number that can receive text messages can also be associated with the user's account so that codes can be sent for two-factor authentication. These other devices or phones can also receive alarms from the sewing machine when other attempts to access the machine fail, such as after a predetermined number of attempts to access the sewing machine. If the sewing machine is believed to have been stolen, these other devices can be used to determine the machine's location via GPS sensors in the sewing machine or by other means, such as a local network detected by the sewing machine. Furthermore, alarms generated due to the machine being moved from its normal location or failed attempts to enter the machine can include the sewing machine's location determined by onboard GPS sensors, allowing the sewing machine to be restored in the relevant circumstances.

[0057] To process and act upon the various data provided by the aforementioned sensors to one or more computers located inside and / or outside the sewing machine, various artificial intelligence (“AI”) tools and technologies (e.g., see...) are used. Figure 19 This enables the analysis of very large, structured or unstructured, and changing datasets, deductive or inductive reasoning, complex problem solving, and computer learning based on historical patterns, expert inputs, and feedback loops. As used in this paper, "artificial intelligence" refers to a broad range of tools and techniques in computer science that enable computers to learn and improve over time. Figure 19 A non-exhaustive overview of these tools is shown, including symbolic artificial intelligence, machine learning, and evolutionary algorithms. Figure 19As shown, artificial neural networks can be used in various machine learning applications and employ a variety of learning methods, including but not limited to statistical learning, deep learning, supervised learning, unsupervised learning, and reinforcement learning. Artificial intelligence enables sewing machines to adapt to situations that software programmers did not anticipate or accurately predict, and facilitates complex yet intuitive ways of interacting with the sewing machine to achieve desired results. That is, the AI ​​tools and techniques described herein are used by one or more computers integrated inside or outside the sewing machine to make decisions that support or benefit the user based on data provided to the computer via the sensors described herein. While specific artificial intelligence tools (such as neural networks) may be described below, other artificial intelligence tools can be used for the same tasks; therefore, unless otherwise stated herein, the description of a tool or technique should not be construed as limiting its application to that tool or technique.

[0058] The related neural network diagrams and processes are as follows: Figures 20 to 23 As shown. The "neural network" used in this paper includes, but is not limited to, multiple interconnected software nodes or neurons arranged in multiple layers, such as... Figure 20 The input layer, hidden layer, and output layer are shown. Figure 20 A schematic diagram of a neural network 128 is shown, which includes nodes 130 arranged in various layers. Like neurons in the human brain, each node 130 may have one or more input connections 132 and output connections 138 to establish many-to-many relationships with other nodes 130 in the network. That is, the output of a single node can be connected to the inputs of multiple different nodes, and a single node can receive the outputs of multiple different nodes as input.

[0059] Each node 130 in the network is configured to compute data from other nodes and, in conjunction with node parameters adjusted during neural network training, compute output data. Figure 21In other words, each node in the network is a computational unit with one or more input connections for receiving input data from nodes in the preceding layer of the network, and one or more output connections for transmitting output data to nodes in the following or next layer of the network. Each node 130 includes a computational unit 136 for computing the result of an activation function that can combine the input data received via the input connections, the input parameters associated with each input connection, and optional function parameters 134 to compute output data that can be further modified by the output parameters. For example, the input data from each input connection can be modified by the associated input parameters, such as the weight parameters of the input connection, to provide the relative weights of the input connection. The result of the activation function, which can be modified by the optional function parameters, can be transmitted as output data to nodes in subsequent layers of the neural network via the output connections. The optional function parameters can be, for example, a threshold, such that when the combined weighted input data exceeds a threshold set by the threshold, the computation result of the activation function is transmitted only as output data to other nodes.

[0060] All forms of data available to the sewing machine—data from sensors, software, data storage devices, user input via software, etc.—can be processed through a neural network. The information to be processed first encounters the input layer, which performs initial processing of the input data and outputs the results to one or more hidden layers to process the output values ​​from the input layer. The information processed by the hidden layers is presented at the output layer as a confidence probability of a given result, such as the location and classification of a detected object in an image. The software in the sewing machine's computer receives information from one of the multiple layers of the neural network and can take corresponding actions to adjust the sewing machine's parameters and / or notify the user based on the results of the neural network processing. Figure 22 ).

[0061] During the training of neural network 128, the node parameters (i.e., at least one of the input parameters, function parameters, and output parameters) of each node in the neural network are adjusted using the backpropagation algorithm until the output of the neural network corresponds to the expected output of a set of input data. Now refer to Figure 21The diagram illustrates the process of training a neural network. The training process begins with node parameters, which can be randomized or transferred from an existing neural network. Data from sensors is then presented to the neural network for processing. For example, an object can be presented to an optical sensor to provide visual data to the neural network. The data is processed by the neural network, and the output is tested, allowing the node parameters of the individual nodes to be updated, increasing the confidence probability of the detections and classifications performed by the neural network. For instance, when a foot is presented to an optical sensor for recognition by the neural network, the network will present a confidence probability that the object shown to the optical sensor is within the coordinate range of the image and can be classified as a specific foot. During the training process, the node parameters of the neural network's nodes are adjusted, making the network more confident that a particular answer is correct. Thus, the neural network begins to "understand" that a particular answer is the most correct answer when presented with certain visual data, even if the data is not exactly the same as previously "seen" data.

[0062] A neural network is considered "trained" when its decisions achieve a desired level of accuracy. A trained neural network can be characterized by the set of node parameters adjusted during training. This set of node parameters can be transferred to other neural networks with the same node structure, causing those other neural networks to process data in the same way as the initially trained network. Therefore, a neural network stored in the data storage device of a specific sewing machine can be updated by downloading new node parameters, such as... Figure 23 As shown. It should be noted that the node parameters of a neural network (such as input weight parameters and thresholds) tend to occupy significantly less storage space than an image library used for comparison with images or visual data acquired by an optical sensor. Therefore, neural network files and other critical files can be updated quickly and efficiently through the network. For example, the structure of the neural network, i.e., the connection graph between nodes and the activation function computed in each node, can also be updated in this way.

[0063] Neural networks can also be continuously trained to periodically update node parameters based on feedback from various data sources. For example, node parameters of a neural network, stored locally or externally, can be periodically updated based on data collected from sensors that may or may not align with the network's output. These adjusted node parameters can also be uploaded to a cloud-based system and shared with other sewing machines, allowing the neural networks of all sewing machines to improve over time. Input data for the neural network can also be shared with servers or cloud-based systems to provide further training information. The vast amounts of data from live sewing machines can be used to train and improve the accuracy of neural network predictions.

[0064] Now refer to Figure 96An exemplary process 200 for controlling a sewing machine 100 is illustrated. Process 200 includes the following steps: acquiring data 202, storing the acquired data in a data storage device 204, processing the acquired data via a neural network 206, and controlling the sewing machine 208 based on the processed data. The acquired data is related to at least one of the following: the sewing machine, the workspace or environment surrounding the sewing machine, the sewing material (e.g., thread and workpiece), the sewing operation performed by the sewing machine, and user interactions with the sewing machine (e.g., recorded by a user interface or other sensors). The neural network includes multiple nodes, each including input and output connections, node parameters, and a computational unit. Based on the processed data, the user interface can be controlled to interact with the user (e.g., by presenting alarms and / or prompts), the data storage device can be controlled to store the processed data (e.g., as a separate record or by updating neural network parameters), and adjustable components can be adjusted to change the current state of the sewing machine (e.g., changing motor speed, turning on a light, moving the needle, or any other action that changes the sewing machine or the sewing operation performed by the sewing machine). Figure 22 As shown, data collected by the sewing machine's sensors can be processed locally on the sewing machine or via an external processor in a cloud-based neural network. The locally stored neural network can be pre-trained or continuously updated. The sewing machine's software then uses the data processed locally or remotely by the neural network to make decisions that lead to machine and / or user interactions.

[0065] Techniques employing one or more neural networks or other artificial intelligence tools can also be used to calibrate cameras and other data acquisition devices (such as sensors). Figure 23B An exemplary camera calibration method is described. Camera calibration can run at any relevant time, such as during sewing machine startup, during sewing machine use, or at any user-defined point in time. Camera calibration can run automatically without any user input. Camera calibration can also be manually initiated by the user. The user can also fine-tune the position of the calibration point.

[0066] To perform camera calibration, the camera acquires data from one or more predefined areas on one or more objects associated with the sewing machine. This data can be any relevant data that can be used for camera calibration, such as visual or image data related to the geometry, color, contrast, or reflection of one or more predefined areas or portions thereof. The one or more predefined areas on the one or more objects used for calibration have known characteristics, such as known geometric features (e.g., distance and angle) and / or known color and contrast characteristics (e.g., hue, saturation, and brightness). Color and contrast references are used to calibrate the camera's image settings (i.e., saturation, white balance, temperature, etc.). For example, geometric references are used to calibrate the camera's focus.

[0067] The camera can acquire data associated with any suitable object, such as one or more of the following: needle bar, presser foot, presser foot ankle, needle plate, needle, paper or plastic sheet, or other sewing machine features and / or accessories (e.g., fabric, projected images, and any movable object associated with the sewing machine). Calibration can acquire data using a single image or multiple images, including images illustrating the two-dimensional or three-dimensional directional motion of the object.

[0068] Surface reference patterns can include, but are not limited to, any camera-detectable surface variation with a defined geometry and location, and can include, for example, holes, edges, lines, and shapes engraved, stamped, embossed, debossed, etched, cut, or painted on a sewing machine or sewing accessory. Surface reference patterns may or may not be used with the area used for calibration. For example, in some cases, one or more objects used for calibration (e.g., presser feet) may already have a unique topology that provides sufficient information, thus eliminating the need for a surface reference pattern. If such an accessory is used, color and contrast references can be obtained simultaneously from another location, such as from the needle or needle plate, as needed. In this case, multiple references can be used for robustness.

[0069] Data acquired by one or more cameras from one or more predefined areas is sent to one or more computers on a sewing machine, or to one or more other processing units associated with the sewing machine. The one or more computers process the data using one or more prediction algorithms, such as in the hidden layers of one or more trained neural networks or in another keypoint method. The one or more neural networks are trained to detect and recognize one or more objects using one or more known features (e.g., geometry, color, contrast, topology, etc.) of the one or more predetermined areas used.

[0070] The prediction algorithm groups object features (including a final reference pattern selected and assigned for camera calibration) and identifies intersections of features, including radial and tangential intersections; either these intersections already exist or are inferred to be intersecting. Regions of interest for potential lines can be pre-trained in the neural network. For example, if lines on a needle plate are to be used as calibration features, finding these lines and inferring them if necessary is relatively quick because the entire image does not need to be computed; only the predefined regions of interest are processed.

[0071] One or more prediction algorithms provide a confidence probability of accuracy for known features. In other words, one or more prediction algorithms compare known features in data provided by one or more cameras with previously learned known features from one or more neural networks and calculate one or more accuracy prediction percentages to quantify the similarity between one or more data features provided by one or more cameras and the learned features.

[0072] The acceptability threshold level can be set to any desired level. If the calculated percentage of accurate predictions (i.e., the probability) is below the acceptable threshold, one or more camera settings are fine-tuned, and the process is repeated, with one or more cameras acquiring more data and the algorithm running again on the new data. This process can be repeated multiple times until an acceptable probability is reached. If the acceptable probability is not reached, an alert signal or message can be sent to the user, requiring them to ensure that one or more objects to be identified are within the full field of view of one or more cameras, that lighting conditions are acceptable, that there are no obstructions, and that the relevant camera calibration surfaces are free from unacceptable contamination. If the acceptable probability is still not reached after completing the above steps, a service alert message (e.g., requiring lens cleaning or other issues that can only be handled by service technicians) can be sent to the user, workshop, and manufacturer.

[0073] If the algorithm determines that one or more features in the data are within an acceptable threshold for the percentage of accuracy prediction, then those features are used to estimate parameters for camera lens and image sensor calibration, and can be adjusted by software to correct the final lens and sensor image quality. For example, various parameters related to one or more cameras can be adjusted, such as, but not limited to, focus, image format, focal length, tilt, distortion, image center, color / intensity, exposure, temperature, and brightness.

[0074] As an example of a calibration procedure, upon startup, the camera can acquire an image of the presser foot currently mounted on the sewing machine. The image is sent to a neural network, which identifies the currently mounted presser foot based on its geometry and color encoding. The color detected by the neural network on the presser foot (e.g., orange) differs from the color (e.g., red) identified on the same presser foot in multiple earlier sewing processes (where image settings and predicted presser foot IDs are considered acceptable). The camera settings can then be modified so that the image data displays red.

[0075] Now refer to Figures 24 to 33 and Figures 104 to 105This document illustrates various views and diagrams related to the use of artificial intelligence in sewing machines to control the position of stitches made in the fabric during the sewing process. During normal sewing operations, the position of the stitches is typically left to the user. That is, various visual aids can be provided to the user, such as guides on the needle plate, projected guides, markings on the workpiece, etc., and the user decides to keep the sewing path in the correct position. However, visual aids cannot control the position of the workpiece, so the final position of any stitch depends on the user's skill in keeping and guiding the fabric in the correct direction. However, the sewing machine described herein can use one or more optical sensors and depth sensing systems (which will be described in more detail below and may include optical sensors, projectors, ultrasonic and thermal vision systems) to find the desired path on the workpiece and can manipulate the lateral position of the needle bar and workpiece via the feed dogs, thus placing the stitches along the desired path even if the user happens to move the workpiece off the thread. Feed dogs used to influence the workpiece feed direction can include linear translational feed dogs, linear translational feed dogs combined with circular rotary feed dogs, and multi-part feed dogs with two or more independent moving parts, such as left and right portions that translate by different distances and / or speeds (similar to a fuel tank pedal) to turn the workpiece during feeding. The two or more parts of the feed dog can also be arranged at different heights to accommodate fabrics of different thicknesses sewing together.

[0076] When sewing, it is usually necessary to create stitches along the seams that have already formed between two or more pieces of fabric, such as... Figure 24 As shown. Sewing along the groove is colloquially called "stitching in" because the two fabrics tend to rise from the seam, resulting in a long, low groove with a relatively deep wedge-shaped cross-section between the two pieces of fabric. Forming stitches along the groove helps conceal the stitches in the finished quilt. Maintaining a constant stitch position along the groove is quite challenging because it is a moving and very narrow target. Threads that slightly match the color of the surrounding quilt pieces or even transparent thread can be used to try and conceal the thread in case of missed stitches.

[0077] Now refer to Figure 25 The field of view of the sewing machine's optical sensor or optical sensor and depth sensing system covers Figure 24 On the image. For example... Figure 104As shown, the user begins sewing and activates the "sewing into the groove" function. When the workpiece is placed on the sewing table, data is continuously collected by sensors and processed by a neural network. The collected data includes data from cameras pointing upstream and / or downstream of the needle drop position towards the sewing area, data related to the sewing operation (e.g., stitch type and parameters), thread data (e.g., thread tension), and data related to the sewing material (e.g., feed rate, motion vector, and workpiece topology). The data is processed by a neural network trained to detect and identify grooves formed between two or more pieces of fabric. That is, the neural network provides confidence probabilities regarding the location and appearance details of the groove. When the user begins sewing, for example by pressing a foot pedal, pressing a button, issuing a voice command, etc., and moves the workpiece to the needle position, the sewing machine detects and identifies the groove and controls the position of the stitches formed on the workpiece by the oscillation of the needle bar and / or the lateral feed of the workpiece, thereby forming stitches along and within the groove. Figures 26 to 33 The actuator shown can be used to change the lateral position of the needle bar, thereby causing the needle to pass through the groove to form a needle foot. It can also be used when moving the workpiece. Figures 30 to 33 The actuator shown controls the feed dog to slightly laterally move the workpiece during its normal forward and backward feed. In other words, the feed dog can move on two axes, thus changing the direction of the sewing path in addition to the workpiece feed rate normally controlled by the feed dog.

[0078] Now refer to Figure 105A process similar to "grooving" can be used to form stitches at a predetermined offset distance or tolerance of a workpiece feature. As the workpiece is placed on the sewing table, data continuously acquired by sensors is processed by a neural network. The acquired data includes data from cameras pointing upstream and / or downstream of the needle drop position towards the sewing area, data related to the sewing operation (e.g., stitch type and parameters), thread data (e.g., thread tension), and data related to the sewing material (e.g., feed rate, motion vector, and workpiece topology). The data is processed by a neural network trained to detect and recognize workpiece features such as edges, seams, "grooves" between two pieces of fabric, buttonholes, pockets, etc. In other words, the neural network provides confidence probabilities about the location of the feature and its appearance details. When the user begins sewing, for example by pressing a foot pedal, a button, or issuing a voice command, and moves the workpiece to the needle position, the sewing machine detects and recognizes the feature, and controls the position of the stitch formed on the workpiece by the oscillation of the needle bar and / or the lateral feed of the workpiece, thereby forming a stitch at a predetermined offset distance from the recognized feature. For example, a user can specify a half-inch stitch tolerance and begin sewing with the workpiece if the edge is positioned within the lateral movement range of the needle bar. As the workpiece moves through the sewing machine, the edge is detected and a stitch is formed half an inch from the edge, without the user needing to precisely follow the edge guide.

[0079] Now refer to Figures 34 to 39 The diagram illustrates various computer vision systems. In addition to visual data provided by optical sensors, neural networks can also receive input from depth-sensing systems to provide more accurate calculations of the location of grooves and 3D topology. Depth-sensing systems can use any of, but are not limited to, stereo vision techniques and other computer vision techniques. Figures 34 to 39 The techniques shown use two optical sensors, two optical sensors and a projector, a projector and a single optical sensor, an optical sensor and a laser light source, a thermal vision system, or an ultrasonic vision system to calculate the distance to the workpiece. Now refer to... Figure 34 This paper illustrates a passive stereo depth sensing system that uses two cameras similar to human stereo vision to determine the distance to a target object based on a comparison between two images captured by the cameras. Figure 35 The active stereo vision system shown is similar, but includes a projector for projecting graphics onto a target object to enhance distance measurements between the two cameras. Figure 36 The structured light vision system also uses a projector to project lines or other visual patterns onto the target object. The camera can observe these lines or patterns to determine the distance from the camera to the target object. Another depth-sensing system is... Figure 37As shown, the system uses a camera to calculate the distance to the target object. The camera measures the time it takes for light from a laser to travel from the laser to the target object and back to the camera. This distance information can also be fed into a neural network that processes visual data of the workpiece from an optical sensor to calculate the location of the groove when the workpiece moves under the sewing head to form a stitch in the workpiece. In other words, the line connecting the points on the workpiece furthest from the sewing head can be identified as the groove in the fabric.

[0080] It should also be noted that the aforementioned optical sensors and depth sensing systems can have a variety of applications. That is, one or more optical sensors and depth sensing devices can be used to identify the topology of fabrics and threads in three dimensions to identify the type of fabric material and thread already used in the workpiece. The density and type of fabric material can also be determined using an ultrasonic or thermal vision system, which can be part of the depth sensing system. That is, denser materials respond differently to ultrasonic pulses than lighter materials. Lasers, infrared radiation, or certain other heat sources can be used to heat a portion of the workpiece, which can be detected by a thermal vision system including, for example, infrared sensors. Therefore, the thermal conductivity of the fabric can be measured and compared to known values ​​for different types of fabrics. This functionality is particularly useful during embroidery when working with existing needles. The information provided by these systems can also be used to identify the type of fabric and thread used in the workpiece to automatically adjust the sewing machine for sewing that type of material and recommend specific needles or other accessories that can be installed in the machine for that workpiece. Automatic lighting adjustments can be made so that the sewing machine user and sensors can view the workpiece material in a manner particularly suitable for sewing (i.e., lower light levels improve the visibility of highly reflective fabrics). Furthermore, as described in further detail below, the sewing machine can provide suggestions and even warnings to the user based on the identified combination of thread and fabric type. The 3D topology of the workpiece can also be used to determine when to release the pretension on the presser foot to more easily climb through multiple layers of fabric, such as when sewing a hem.

[0081] Processing distance information alongside visual data using neural networks further improves accuracy, as the neural network can be trained to consider the workpiece's appearance and shape when determining the groove location. The neural network used to process the visual and distance data can be trained elsewhere, and during the sewing process, it can be processed via a cloud computing connection to the sewing machine's computer. Figure 23The node parameters and other necessary information transmitted to the sewing machine are used for training the neural network. For example, the same or additional optical sensors can be used to observe the stitches formed in the workpiece to identify missed stitches. When the computer knows the sewing pitch, it can determine the control data for a specific missed stitch and use it to adjust the node parameters of the neural network to reduce the chance of a missed stitch. The computer on the sewing machine can work in conjunction with a cloud-based neural network, which can provide additional computing power to process the data provided to the neural network and train the neural network during the operation of the sewing machine, making the neural network a continuously learning neural network.

[0082] The aforementioned techniques for precisely forming "sewing grooves" can be more broadly applied to sewing in a wide variety of situations to create "perfect stitches." That is, data from one or more optical sensors and depth sensing systems can be processed via neural networks to provide control data to one or more motors and actuators of the sewing machine to precisely and accurately form any type of desired stitch at any specific location on the workpiece. In addition to using visual data from optical sensors and depth sensing data from depth sensing systems, the perfect stitch control system can consider data from thread tension sensors, needle position sensors, needle force sensors, fabric feed rate sensors, the speed and frequency of needle bar movement, the pressure applied by the presser foot, the feed rate of the feed dog, and so on. Data from these sensors can be processed by neural networks to predict whether incorrect stitches are likely to be produced and can guide the control system to adjust various parameters accordingly to compensate for any factors that may cause errors. In processing the data provided by these sensors, the sewing machine's computer can use decision information from the neural network to adjust various sewing parameters, such as thread tension, needle position, force, speed and time, stitch length and type, motor speed, and fabric feed settings, to actively achieve ideal stitch precision and accuracy. All these features can be combined to correlate machine performance with the user's skill level. That is, the sewing machine can learn to work with beginner, intermediate, and advanced users, adapting to the machine's speed, the presentation of corrections and alarms, and the recommendations for guidance or assistance provided to the user.

[0083] As in the example of sewing in grooves above, the sewing machine can also inspect for errors in the formed stitches. That is, for quality purposes, each completed stitch can be actively monitored. If data collected by the sewing machine's sensors indicates that an imperfect stitch has been formed (e.g., a skipped or misaligned stitch), the output data generated by the neural network can be used to make decisions about adjustments to the sewing machine's parameters. These adjustments can be made, and the resulting stitches can be monitored until the formed stitches are perfect. Sensors can also be used to detect thread breaks so that sewing can be stopped and the thread replaced. Therefore, as the neural network is continuously trained, the quality of the stitches can improve over time. For example, zigzag stitches can be controlled to maintain a specific width on either side of a fabric seam, thus forming continuous stitches in opposing fabric pieces. Or, when performing simple straight stitches, the tension of the upper and lower threads can be controlled to prevent the stitch from passing through one side of the workpiece. Optical sensors can also identify lines of a pre-existing pattern that are part of a pattern on a workpiece (e.g., by weaving into the fabric or printing on it), stretched, superimposed, stretched, or projected onto the fabric, thereby forming stitches along or at a constant offset distance from that line. In other words, optical sensors can be used to detect the edges of the fabric and help the user sew along those edges with constant stitch tolerances. Two or more pieces of material may have edges that the user attempts to align during sewing; the sewing machine can detect misaligned workpieces and suggest corrections to the user.

[0084] Figure 106An example of a process for detecting and adjusting sewing errors is illustrated. As the user sews, data is continuously acquired from cameras pointing upstream and / or downstream of the needle drop position towards the sewing area, sewing operations (e.g., stitch type and parameters), thread data (e.g., thread tension), and sewing material (e.g., feed rate, motion vector, and workpiece topology). Input data can also be provided from a database of known sewing errors and their causes; for example, pleats can be caused by an imbalance in thread tension between the upper and lower threads. This data is processed by a neural network trained to recognize sewing errors, and the identified errors can be recorded along with contextual information (e.g., sewing machine parameters at the time of the error or workpiece movement at the time of the error) and reported to the user. The recorded information can be used to update local and remote neural networks to improve error detection and prediction. The sewing machine can also control actuators or motors in response to identified sewing errors to correct errors in the next stitch or prevent similar errors from recurring. A non-exhaustive list of sewing errors includes skipped stitches, uneven stitches, misaligned stitches, seam wrinkles, variations in stitch density, broken bobbin thread, broken looper thread, broken needle thread, melted thread, broken needle, stuck needle, needle hitting the needle plate, thread being cut by the needle, inconsistent thread tension, wavy seams, no needle, loose needle holder, loose presser foot, misaligned presser foot, needle unable to move, workpiece unable to move, workpiece tangling, thread tangling, knotted thread, loose stitches, tangled thread, worn thread, torn thread, variations in workpiece feed, bent needle, damaged looper, damaged needle finger, misaligned looper, misaligned needle finger, and dulled fabric cutter.

[0085] A continuously trained neural network—one that is trained and adjustable during the sewing process—can ultimately adjust many parameters of the sewing process in unpredictable ways to compensate for unforeseen problems that are very difficult or impossible to predict and resolve through traditional control software or by the user adjusting sewing machine settings. For example, the sewing machine can adjust the feed rate and sewing pitch in response to external forces applied by the user, which would otherwise pull the workpiece off the thread. In doing so, the neural network can also determine that adjustments to thread tension or presser foot pressure are useful. In other words, the sewing machine can learn to compensate for and even resist incorrect movements by the user to further ensure that the stitches formed are accurate and precise.

[0086] The sewing machine's projector can be used in conjunction with the artificial intelligence technologies described in this article to improve the positioning of the image projected onto the workpiece. For example, such as... Figure 107As shown, a neural network can be used to identify features of a workpiece, allowing a sewing guide to be projected at the location of the feature or at a predetermined distance from it. As the workpiece is placed on the sewing table, data continuously acquired by sensors is processed by the neural network. The acquired data includes data from cameras pointing upstream and / or downstream of the needle drop position towards the sewing area, data related to the sewing operation (e.g., stitch type and parameters), thread data (e.g., thread tension), and data related to the sewing material (e.g., feed rate, motion vector, and workpiece topology). The data is processed by a neural network trained to detect and identify features of the workpiece, such as edges, seams, grooves between two pieces of fabric, buttonholes, pockets, etc. In other words, the neural network provides confidence probabilities about the feature's location and its appearance details. When the user begins sewing, for example by pressing a foot pedal, a button, or issuing a voice command, and moves the workpiece to the needle position, the sewing machine detects and identifies the feature and controls the projector to project the sewing guide, for example, a straight line in the feed direction at the feature's location or at a predetermined offset distance from the identified feature. For example, a user can specify a half-inch stitch tolerance and activate a sewing guide that projects a line half an inch from the edge of the workpiece as the user moves the workpiece, allowing the user to correct the lateral position of the workpiece to form a stitch in the desired location.

[0087] Now refer to Figures 40 to 42 This illustrates various views and diagrams related to the use of artificial intelligence in sewing machines to predict the path of stitches being formed, projecting a predicted stitch image onto the fabric before the needle position to inform and guide the user. As with the stitch adjustment and control features described above, optical sensors acquire visual data from the fabric workpiece and provide that data to a computer. The computer processes the data via a neural network trained to predict the sewing path based on visual data related to the already formed stitches and parameters of the sewing machine, such as needle position and speed, fabric position and speed, feed dog rate, force applied by the presser foot, tension of the upper and lower threads, speed selected by the user, etc. The neural network processes the data and provides the predicted sewing path to the sewing machine's computer, which then projects a series of stitches along the predicted path in front of the needle. The user then communicates with the sewing machine through a user interface (…). Figure 40 The selected pin type is merged into the projection view. Figure 41The projected path of the stitches is displayed so that the user can see the shape of the stitches formed along the predicted sewing path. As the user or the fabric translation section of the sewing machine moves the workpiece, the projected path of the stitches also moves, thus ensuring the path appears in a constant position on the workpiece. (In embroidery machines, the projected embroidery pattern can move with the workpiece as the embroidery frame moves.) The predicted path can also be adjusted to suggest that the user follow the path back to a deviated pattern. The projected path of the stitches can also start from the point of needle placement and extend in a straight line or curve in the feed direction, which does not move when the workpiece rotates or translates.

[0088] Now refer to Figure 42 The predicted stitches are shown in black projection, while the actual stitches are shown in blue. The projected stitches appear to be swallowed up by the actual stitches forming in the workpiece. Users can also set the prediction distance to show only a few predicted stitches or to show lines of stitches extending to the limits of the projector's range. Embroidery patterns can also be projected in a similar manner, so that the projected stitches disappear as the pattern forms in the workpiece. As the workpiece, held by the embroidery frame, moves, the projected image also moves to track the workpiece, so that the needle follows the projection of the predicted sewing patch.

[0089] The predicted stitch path projected along the workpiece in front of the needle offers numerous advantages. In some cases, the user may wish to place a smooth stitch curve that terminates near or at a distance from an existing feature of the workpiece. Alternatively, the user may wish to avoid contact with or overlap with existing features of the workpiece. In these situations, the predicted sewing path, moving with the workpiece, will help create the desired seam in a single channel. Additional information can be provided beyond the predicted sewing path. For example, the projected stitch may change color if the predicted projection path encounters or comes too close to a feature of the workpiece that the user has specified as an object to avoid, or if the sewing machine identifies and predicts a feature the user wishes to avoid (e.g., needles, buttons, additional seams, buttonholes, decorative elements, fabric edges, etc.). In these scenarios, the projected stitch may also flash and can be combined with other notifications, such as auditory or tactile feedback discussed in this disclosure. Alternatively, the projected path can be automatically altered by the sewing machine to guide the user around obstacles, with the original path and the new, altered path projected in different colors, and / or with motion cues that clearly indicate the path has changed, such as by flashing near the path or animating arrows near the path.

[0090] Such warning signals can also be sent if the user's finger moves into the predicted sewing path or the path of other parts of the sewing machine (such as the presser foot or connecting accessories). It should be noted that the projector is not limited to projecting only the predicted sewing path; it can also project many other symbols and / or words near the path to notify and alert the user to changes in the path or obstacles. For example, a neural network can identify buttons on fabric and provide the computer system with the button's position and size data, allowing the computer to instruct the projector to project the button's outline around the button on the workpiece, thereby drawing the user's attention to that feature.

[0091] As a last resort, if an obstacle is about to be hit by the needle and the user does not respond (e.g., via a touchscreen interface or a voice control system) to avoid the obstacle, the sewing machine can be stopped completely. Figure 108 A flowchart illustrates the use of a neural network during sewing operations to prevent injury to the user or damage to the sewing machine. As the user begins sewing on the machine, data is collected from a camera pointing towards the sewing area, and also from other sensors, such as one or more microphones listening to the environment to capture audio cues or other expressions from the user. The collected data is processed by a neural network trained to detect foreign objects that may damage or harm the sewing machine. For example, the neural network can identify a user's finger under the presser foot or in the needle path. Audio data can also help determine if the user is having a conversation and may be distracted, increasing the likelihood of unintentionally placing a finger or hand. Once an object is detected, the sewing machine can alert the user and stop sewing or lower the presser foot to avoid injury to both the user and the machine. Foreign objects may not be directly in the sewing path but may be nearby, causing the sewing machine to generate an alarm. For example, as mentioned above, the sewing machine can alert the user audibly or project a warning onto the workpiece. If no foreign object is detected, the sewing operation proceeds normally.

[0092] In addition to compensating for deviations from the desired sewing path, neural networks can be used to analyze data collected by the sewing machine during a user's sewing process to assess their skill level. For example, frequent deviations from the desired sewing path might indicate a novice user, while fewer deviations might suggest an expert. The sewing machine can then suggest guidance and training exercises for improvement. Feedback can be shared in any single or combined manner, including audio, text, video, image projection, and augmented reality configurations from the sewing machine or connected devices. Adjustments to the sewing machine settings can also be suggested to improve the sewing of novice sewing machine operators and increase the efficiency of expert sewing machine operators. The sewing machine can also provide new opportunities and challenges for advanced users to help them further improve and expand their skills.

[0093] Figure 109 An exemplary flowchart illustrating the problem of using a neural network to detect threads is shown. When a user uses the sewing machine in any way, data is collected from user-facing sensors (such as cameras), real-time user interactions with the user interface, logs of historical interactions with the sewing machine, and information related to the current sewing operation (if any). As described above, the collected data is processed by a neural network trained to detect the user's skill level. If the neural network has assessed the user's skill level, the sewing machine can continue to warn the user that the task is more difficult than the detected skill level or that helpful tips or hints can be appropriately provided. As described above, the sewing machine can also provide recommended training exercises based on the detected user skill level.

[0094] The analysis of a user's skill level can also be applied to the interaction between the user and the sewing machine. That is, the sewing machine can detect, through neural network analysis, the characteristics of a user struggling to use the machine correctly, and can suggest tutorial videos or instructions, and provide on-screen prompts to help the user understand which user interface control to interact with next. User interaction data can include the aforementioned user-facing camera data, and can also include time information from the user interface, indicating the speed at which the user interacts with the sewing machine's settings. The time a user spends interacting with the sewing machine can be an indicator of the user's skill level; that is, a user who selects menu items more quickly in the user interface may be more familiar with the sewing machine, and combined with other data, this can help the sewing machine identify the user's estimated skill level. For example, after activating a feature, the sewing machine can highlight a button and display a pop-up message prompting the user to take the next step to use the activated feature. Input from user-facing camera and facial recognition technologies provides further input about the user's emotional state when interacting with the sewing machine. That is, when the user appears frustrated or confused, graphical and audio prompts can be provided. Alternatively, the sewing machine can avoid providing further prompts that may be considered annoying and useless, in order to best support and guide the user in solving any problems they are trying to solve.

[0095] Based on data collected from monitoring sewing machine usage, the sewing machine can also provide helpful recommendations for other products or accessories. Product advertising can be done in any single or combined manner, including audio, text, video, image projection, and augmented reality configurations from the sewing machine or connecting device. When recommending products, the sewing machine or external processor collects and monitors data through real-time or retrospective data analysis, particularly the frequency and preferences of users' chosen sewing accessories, programs, and machines. For example, the sewing machine can keep track of the usage of each type of thread and understand typical thread purchases, suggesting the purchase of more thread when supply is estimated to be insufficient. Another example is that when a user uses a particular presser foot for a certain purpose and a more suitable presser foot is available, the sewing machine can suggest purchasing a more suitable option if the user has not entered it into their current list of sewing accessories. The list of sewing accessories can be stored on one or both of the applications on the sewing machine and connecting device. This data can be sent back to the manufacturer so that engineering, marketing, and customer service teams can improve the quality of the sewing machine and other products.

[0096] Now refer to Figures 43 to 65 This illustrates various views and diagrams related to the use of artificial intelligence in sewing machines to identify the textile materials of the thread and workpiece used in the machine, in order to adjust sewing parameters and provide the user with information about the combination of thread and fabric identified by the sewing machine. Now refer to Figures 43 to 49 The image shows a portion of a sewing machine, illustrating how thread can travel along it from a spool mounted on top of the sewing machine. Figures 43 to 45 ) and from the bobbin mounted below the needle plate (see Figures 46 to 49 The path to the sewing needle.

[0097] Sewing machines can include various sensors along these thread paths to detect the type of thread the user has installed in the machine. These sensors can include, but are not limited to, RGB sensors, light sensors, optical sensors such as cameras, etc. Illumination sources and magnifying lenses can also be equipped with specific sensors. For example, such as... Figure 50 As shown, an optical thread sensor can be included at the top of the sewing machine arm and behind the spool mounting location. Figure 87An exemplary thread sensor 140 is shown, comprising a tubular housing 142 through which a thread 141 passes. The tubular housing 142 blocks ambient light from shining onto the thread 141, thus providing a light source 144 to illuminate the thread 141 for detection using an optical sensor 146 (e.g., a camera or RGB sensor) for collecting thread data. The sewing machine may also include sensors for detecting thread parameters and mechanisms for adjusting those parameters. The tubular geometry of the sensor assembly provides a known background for illuminating the thread, thereby improving the accuracy and precision of thread information acquired by RGB or other sensors. Sensors disposed within the tubular housing can detect light, sound, or other parameters of the thread to determine its color, density or weight, surface quality, material or fiber type, and overall quality. That is, RGB or other sensors can be used to detect the inherent characteristics of the thread as it passes through the sensor housing.

[0098] Data collected by the thread sensor is transmitted to the sewing machine's computer and compared with a thread information database containing information about various thread types and colors. Therefore, the sewing machine can identify the thread and present information the user might not be aware of. If a specific thread can be identified from information on the spool (either manually entered by the user or detected by the machine), the detected thread characteristics can be compared with those stored in the thread information database. Thus, the sewing machine can detect a thread with significantly different characteristics from those stored, potentially indicating a defective spool, and present the same warning to the user. Information on the spool can be collected by optical sensors or other sensors positioned near the spool pins on which the spool is mounted during sewing. Spool information can also be collected when the user holds the spool in front of optical sensors or other sensors positioned in the sewing head or another location (e.g., a camera in the sewing head or one or more cameras facing the user). The time and date of thread identification can be stored and associated with items, stitch types, etc., to establish a thread usage history in the sewing machine.

[0099] The sewing machine may also include sensors for detecting the current state of the thread when the thread is manipulated by the machine, and may include mechanisms for adjusting the sewing machine. For example, the sewing machine may include a thread tension sensor (…). Figures 51 to 54 ), line distribution unit ( Figures 55 to 58 ) and line tension unit ( Figures 59 to 62 Sensors for detecting the inherent characteristics and current state of the thread are arranged to collect data on the quality and condition of the thread as it passes from the spool or bobbin through the thread tensioner, around the hook or other components of the sewing machine, and finally through the needle. As described in more detail below, optical sensors can also be used in conjunction with neural networks to detect the type of presser foot and / or needle mounted on the machine.

[0100] Sewing machines also include optical or other sensors that can be used in conjunction with neural networks to detect material or fiber type, color, reflectivity, pattern, weave direction, orientation (i.e., right side and wrong side), and the topology of the fabric used in the workpiece. Exemplary sensors for acquiring data about the workpiece fabric include a radiation source (e.g., a light source or infrared light source) positioned on the sewing head and pointing downwards at the workpiece. A radiation detector, such as a light sensor or infrared light sensor, is positioned on the sewing table, i.e., below the workpiece. It should be noted that the positions of the transmitter and receiver can be reversed, i.e., by providing the transmitter in the sewing table and the receiver in the sewing head. Thus, the amount or portion of emitted radiation (e.g., visible or infrared light) passing through the workpiece, and therefore the amount of radiation reflected by the top surface of the workpiece, can be detected and measured. Ultrasonic transmitters and receivers can be arranged in a similar manner, i.e., the transmitter on the sewing head and the receiver on the sewing table, to provide a method for determining fabric density more accurately than other techniques. These transmitters and detectors—that is, those for light (infrared radiation (IR), cameras), color (RGB), ultrasound, etc.—can be used individually or together to determine the material or fiber type, density, and reflectivity of the workpiece material. The additional depth sensing techniques described in this paper can also be used to detect the topology of a workpiece.

[0101] Data collected by fabric sensors is transmitted to the sewing machine's computer or any connected external processor and compared with a fabric information database containing information about various fabric types with different colors and patterns. Therefore, the sewing machine can identify the fabric of a workpiece and present information the user might not be aware of. If a specific fabric can be identified from information on a roll of fabric (either manually entered by the user or detected by the machine), the detected fabric characteristics can be compared with stored fabric characteristics from the fabric information database. Thus, the sewing machine can detect fabrics with significantly different characteristics from those stored, potentially indicating defective pieces, and can then present the user with a warning indicating the same issue. Workpiece identification data can be combined with stitch data to train a neural network to associate workpiece features with different stitches. Therefore, the sewing machine can alert the user if a stitch is being formed on the wrong side of a workpiece facing the wrong direction.

[0102] like Figure 63 As shown, the sewing machine's computer processes data collected by the various sensors and other devices mentioned above using a neural network. The neural network is trained to provide suggestions, reminders, and warnings to the user based on the input data. That is, the neural network is trained to recognize compatible and incompatible combinations of thread, fabric, presser foot, and needle types. For example, Figure 64A table showing fabric and thread compatibility is displayed, indicating whether heavy or light fabrics are compatible with heavy or light threads. If the sewing machine detects a potential problem with the combination of thread and fabric, suggestions can be provided to the user on the display, accompanied by audible or tactile notifications. If the potential compatibility problem is more serious, alerts or even warnings can be issued to the user. In some cases, the sewing machine can stop completely, providing a combination of audible, tactile, and visual warnings. In addition to notifying the user of potential compatibility problems, the sewing machine can also make adjustments such as thread tension, presser foot pressure, stitch type, and speed to improve sewing performance when using heavy or light threads and / or heavy or light fabrics. Even when the correct type of thread is selected for a given fabric, the thread color may not be aesthetically pleasing considering the selected fabric color and / or pattern. Therefore, neural networks can also be trained to suggest compatibility of various thread and fabric colors and patterns to the user, such as… Figure 65 As shown.

[0103] Figure 102 An exemplary flowchart illustrating the use of a neural network to identify workpieces and potential workpiece problems is shown. When a user begins sewing on the sewing machine, data is collected from a camera pointing towards the sewing area, the sewing operation, an optical thread sensor, a feed rate sensor, a database of known workpiece or fabric materials, and a log of previously identified workpiece materials. The collected data is processed by a neural network trained to detect workpiece compatibility issues, damage, and other thread quality problems. If the neural network identifies a workpiece that is incompatible with the current sewing operation and other sewing materials (e.g., lightweight thread may break when used with thicker or heavier workpiece fabric), the sewing machine alerts the user. Sewing can continue if the user chooses to reject or ignore the notification. The user is also alerted if workpiece damage or other quality problems are identified. When the damage is sufficient to require user intervention (e.g., replacing or repairing the workpiece), the sewing machine can selectively prohibit further sewing.

[0104] Now refer to Figures 66 to 71 and Figure 101 This illustrates various views and diagrams related to the use of artificial intelligence in sewing machines to identify reduced thread quality, adjust sewing parameters, and provide users with information about the quality of the thread being used. As mentioned above, a sewing machine may include various sensors along one or more paths of the thread in the sewing machine from the thread source to the sewing head, such as those in... Figures 43 to 49 As shown in the diagram. These sensors may include, but are not limited to, RGB sensors, light sensors, and optical sensors such as cameras. The sensors are arranged to collect data on the quality and condition of the thread as it passes from the spool or bobbin through the thread tensioner, around the hook or other components of the sewing machine, and finally through the needle. Additional sensors, such as thermal sensors, may be included to monitor the temperature of various components that are engaged and may cause thread damage.

[0105] Now refer to Figure 66 and 67 Examples of the appearance and characteristics of high-quality and low-quality wires are shown. Wires considered high-quality or in good condition have the following characteristics: tight and strong fibers, consistent diameter, consistent color, consistent reflectivity, and consistent friction. Wires considered low-quality or in poor condition have the following characteristics: loose and worn fibers, inconsistent diameter, inconsistent color, inconsistent reflectivity, inconsistent friction, and poor splicing. Additional light can be provided in or near a sensor, such as the tubular sensor housing 142 described above, to provide a consistent light source when observing the wire, so that the wire is not misdiagnosed based on color changes in varying lighting conditions (e.g., daylight, cool white light, horizon, and incandescent lamps). Figure 68 As shown, when using low-quality thread, one or more optical sensors in the sewing machine can also detect debris buildup in areas of the sewing machine known to accumulate in the sewing machine area.

[0106] Now refer to Figure 69 This document illustrates a flowchart of an exemplary scenario regarding the quality of thread used in a sewing machine. In the illustrated scenario, sensors collect data related to the state of the thread used in the sewing machine. The data is processed by a previously trained or continuously trained neural network to determine if the thread exhibits any signs of low-quality thread. When poor-quality thread is detected, the user is notified via the notification methods disclosed herein. Figure 70 This can be achieved through various means, such as a user interface, computer-generated voice, indicator lights, and haptic feedback. The user can then view the sewing machine's display for or request an auditory description of further details regarding the thread quality. The user can choose to reject a warning or take action, and then continue sewing. In sewing machines with multiple spools, the machine can also track the thread parameters of each spool and can notify the user which spool (if any) contains low-quality thread.

[0107] Figure 101Another flowchart illustrates the use of a neural network to detect thread problems. When a user begins sewing on the sewing machine, data is collected from a camera pointing towards the sewing area, the sewing operation, an optical thread sensor, other thread sensors for measuring thread tension, feed rate, and distribution, a database of known thread materials, and a log of previously identified thread materials. The collected data is processed by a neural network trained to detect thread compatibility issues, damage, and other thread quality problems. If the neural network identifies a thread that is incompatible with the current sewing operation (e.g., the thread might break when used in a particular stitch), the sewing machine alerts the user. Sewing can continue if the user chooses to reject or ignore the notification. The user is also alerted if thread damage or other quality problems are identified. When the damage is sufficient to require user intervention (e.g., thread replacement), the sewing machine can selectively prevent further sewing.

[0108] The sewing machine may also include multiple thread quality sensors, such as one or more sensors 140 disposed in the tubular housing 142 as described above, to determine whether the thread quality changes along the thread path. For example, if a decrease in thread quality is detected after a specific feature of the thread path, the sewing machine may recommend changing sewing parameters to reduce the likelihood of machine-induced thread damage. Monitoring thread quality at multiple locations along the thread path also provides the sewing machine with the opportunity to recommend inspection of various components that may require repair or replacement, such as guides that may have sharp edges that cause thread wear. This monitoring can also allow the sewing machine to identify improper threading based on locations where the thread appears to deviate from its predetermined thread path through the sewing machine.

[0109] Now refer to Figures 71 to 81 This paper illustrates various views and diagrams related to the use of artificial intelligence in sewing machines to distinguish and identify objects placed in the field of view of optical sensors on the sewing machine, providing the user with information about object characteristics and the relationship between the object and the sewing machine. The optical sensor (e.g., a camera) can be a sensor pointed towards the sewing area, or it can be a front-facing or user-facing sensor that allows the user to hold the object in front of the sensor to detect the component. A resource library or database stores the identified objects, enabling the sewing machine to build an inventory of known objects, such as sewing machine components or accessories used with the sewing machine. For example, the sewing machine can identify the type of needle mounted on the sewing machine and whether the needle is correctly installed. Figures 71 to 72 ), the type of presser foot installed on the sewing machine, and whether the presser foot is installed correctly. Figure 73 The type and characteristics of the embroidery frame installed on the sewing machine, and whether the workpiece is correctly installed inside the embroidery hoop. Figure 74 The user's fingers and hands, and whether there are any security risks to the user during the current operation. Figure 75Regarding embroidery hoops, the sewing machine can identify, for example, whether the clamping mechanism used to secure the embroidery hoop is fixed, whether the workpiece is laid flat within the hoop, and whether all fabric edges are outside the hoop. It can also identify the quality of components; that is, the sewing machine can detect whether components are damaged, rusted, bent, worn, incorrectly threaded (in the case of needles and loopers), or otherwise alter the acceptable quality standards of the components. In each of these examples, a neural network is used to process visual data acquired by one or more optical sensors of the sewing machine.

[0110] Now refer to Figure 76 The sewing machine's computer processes data collected by various sensors using a neural network to determine whether the sewing machine has detected a specific object and whether that object should be present. For example, ... Figure 77 As shown, optical data can be captured within a range including the presser foot of the sewing machine. The visual data of the image is processed via a neural network to determine the presence of a presser foot, the type of presser foot present, and whether the presser foot is properly installed. A similar determination can be made for the needles mounted on the sewing machine. Once the presser foot and needle are identified, the translation range of the corresponding needle for the presser foot is stored, and the user can be notified if the combination of needle and presser foot is not recommended. The user can then choose to reject the warning, for example by selecting "Expert Mode," which includes a reminder of the potential safety risks involved in selecting "Expert Mode." The selected needle foot is also compared with the installed presser foot and needle to determine whether the installed presser foot and needle are suitable for and compatible with the selected needle foot or series of needles in the project. If no presser foot or needle is installed, the sewing machine can recommend a presser foot and needle. When installing the presser foot and / or needle, the sewing machine can re-check the presser foot and needle to confirm that the appropriate presser foot and / or needle have been installed and that the needle and / or presser foot are properly installed. The sewing machine can also identify incompatibilities such as between needles and sewing plates, presser feet and selected stitch patterns, and between one or more needles and selected stitch patterns. Incompatibilities between stitch types and presser feet can be provided, for example, in a table or database of incompatibilities, or learned over time by monitoring sewing errors associated with the identification of various components and the sewing operations performed.

[0111] Figure 100Another flowchart illustrates the use of a neural network to detect objects, identify compatibility issues, and resolve installation problems. When a user begins sewing on the sewing machine, data is collected from a camera pointing at the sewing area, the sewing operation, a database of known components and accessories previously used with the sewing machine, and a database of known components and accessories compatible with the sewing machine. The collected data is processed by a neural network trained to detect, classify, and determine whether components and accessories are correctly installed, and whether the combination of components and accessories and the selected sewing operation present any conflicts or other problems. If the neural network identifies a component as incompatible with the sewing operation or potentially causing a problem, it alerts the user and gives the user the opportunity to reject the alert (e.g., similar to the "expert mode" described above). The neural network identifies whether components and accessories are correctly installed. If not, it alerts the user and may prevent the sewing machine from running until the component is removed or correctly installed.

[0112] For embroidery hoops that can be mounted above the sewing table, a similar determination can be made. Once the type and size of the embroidery hoop are determined, the sewing machine can notify the user whether the selected embroidery pattern will exceed the limits of the embroidery frame. The sewing machine can also check the edges of the fabric held within the embroidery frame to detect incorrect fabric mounting within the hoop. In the event of a problem with fabric mounting or embroidery hoop size detected, the user can be notified via any of the notification methods described herein, such as a visual display of information on the sewing machine's monitor, an auditory notification, or tactile feedback.

[0113] When identifying and inspecting embroidery hoops, or when specified by the user, one or more cameras pointed at the sewing table can capture images of the workpiece mounted within the embroidery hoop. The entire workpiece can be captured in a single image, or the embroidery hoop can be moved to capture multiple images of the workpiece, which are then stitched together to form a single image of the entire workpiece. Data acquired during the scanning process can be used as input to a neural network trained to recognize and predict colors. This pre-learned color calibration, as the neural network learns from correct color recognition, contributes to more accurate color predictions over time. Scanning data can also be used as input to a neural network trained to detect translational jumps or other motion anomalies, allowing the actuation system of the embroidery hoop to be controlled to correct these anomalies.

[0114] When attached to a sewing machine, other accessories can also be recognized, and the sewing machine can provide feedback on whether the accessory is installed correctly and whether the machine is configured to operate properly with that accessory. For example, when a user attaches an accessory for attaching a strip to a workpiece to the machine, the sewing machine can display information related to the accessory on the screen to help the user use the accessory correctly. The sewing machine's functionality can also be limited to functions compatible with the accessory, unless the user vetoes these limitations. The sewing machine can also display information on the screen related to materials that can be used with the accessory and can recommend other accessories to the user.

[0115] Now refer to Figures 78 to 81 Various views and schematic diagrams of exemplary presser feet, sewing needles, and other components are shown, including features designed to make the presser feet and needles more easily identifiable by object recognition technologies, such as through the use of neural networks or by sensors including magnetic sensors configured to detect component features. Presser feet, sewing needles, needle plates, or other sewing machine components may include various markings to improve the robustness of optical or other sensor-based object recognition systems. For example, markings or signs may include patterns of two or more geometric shapes (…). Figures 78 to 81 ), color lines at specific locations ( Figure 80 The markings may include the overall shape of the component (including identifiable protrusions or recesses), paint color codes and other color treatments, reflective finishes, barcodes, QR codes, and other surface treatments capable of UV, IR, or other optical sensing technologies. Markings may include unique patterns of etched rings or lines, or shapes or patterns etched, recessed, or embossed on the surface of the sewing machine component. Markings may also consist of different areas of the sewing machine component's surface with different reflectivity and surface finishes; that is, the marking may include a first area with a first surface finish and a second area with a second surface finish. Markings may use electronic identification technologies such as near-field communication (NFC) devices and radio frequency identification (RFID) devices.

[0116] Additional alternative markings can be based on markers with magnetic field line outlines or polarity outlines for each component, which sensors can detect when the components are installed in the sewing machine. For example, a needle may include a magnet for generating a specific magnetic field that is only detected when the needle is inserted into the needle bar. Similar techniques have been applied to embroidery hoops to improve the recognition of such hoops through neural networks or other object recognition technologies.

[0117] Now refer to Figures 82 to 84 This illustration shows various views and diagrams related to providing tactile feedback to users regarding the use of a sewing machine. Tactile feedback is feedback provided to the user in a perceptible manner. For example, it's the control components the user interacts with (e.g., knobs, buttons, pedals, joysticks, sliders, etc.) when reaching a specific position. Figure 83 The components shown may vibrate slightly, or even create resistance to further movement of the controlled object. Small vibrations can also be provided through the surface of the sewing machine, where the user's hand and fingers can rest during use, such as the sewing table. Tactile feedback can be used to alert the user to a specific state of the sewing machine or workpiece, or as further reinforcement of the user's action. For example, the sewing table under the workpiece and the user's hand can vibrate when the user deviates from the desired sewing path. Alternatively, a knob or button can vibrate to indicate that the button has been pressed or the knob has reached a specific position. Tactile feedback can also replace mechanical features that provide similar feedback, such as a latch in a knob indicating that a specific position around the knob has been reached. Tactile feedback can be used on any sewing machine surface. Vibrational tactile feedback via piezoelectric sensors can be used on any surface of the sewing machine and can be used to replace mechanical user interfaces. Piezoelectric and capacitive sensors can be arranged in an array under an organic light-emitting diode (OLED) or similar type of screen, which is formed as an alternative to the traditional plastic sewing machine cover. The presence of a user's finger on or near the OLED interface triggers menus based on user requests, current sewing actions, and relevant user interface requirements. Examples include tapping, sliding, and scrolling movements of the finger for threading, adjusting thread tension, and activating or deactivating sewing accessories. Other forms of haptic feedback may include force, electro-haptic, ultrasonic, air vortex loop, and thermal haptic feedback.

[0118] Now refer to Figure 83 A flowchart illustrating an exemplary scenario where haptic feedback can be used is shown. In the illustrated scenario, a user attaches a presser foot to the machine, which is identified through neural network processing of visual data received from the machine's optical sensors or other sensors. The user then selects a specific pattern or sewing stitch to perform. The sewing machine then determines whether the combination of the specific presser foot and the selected operation is a valid combination, i.e., whether the attached presser foot can be used with the selected specific stitch, and if the combination is invalid, provides haptic and other feedback to the user. This haptic feedback can be provided at the location of the last action, such as when the user selects the stitch or other operation to perform, via a touchscreen. Simultaneously, visual and auditory alerts can be provided to the user that the presser foot and the selected operation are incompatible, prompting the user to install the correct presser foot or select a compatible operation. Figure 84 The interface can also provide users with the option to reject warnings.

[0119] Now refer to Figures 85 to 88This illustration shows various views and diagrams related to the use of artificial intelligence in sewing machines to monitor their mechanical and electrical health. Operating a sewing machine generates a wide variety of sounds and mechanical vibrations, as well as variations in the electrical signals driving the machine's motors and actuators. Exemplary sewing machines include sensors for monitoring sound and noise, mechanical vibrations, and electrical signals to identify patterns related to the performance of relevant components. Sensors may also be provided on or near various components to measure component temperature; elevated temperatures may indicate excessive wear. Figure 85 As shown, sensors are arranged at various locations on the sewing machine. The sensors can be continuously activated, or they can be turned on for specific periods of time to collect data, such as during startup, idle, active, and shutdown.

[0120] The collected data can be processed through a neural network trained to detect performance problems in the components of a specific sewing machine under discussion. For example, certain sounds might be related to friction between two components, which in turn indicates the need to replace bushings or bearings. Or, when motor performance deteriorates, the voltage required to run the motor at a specific speed might be higher than that required when the motor is operating under nominal conditions. Motor performance can be monitored to determine when a problem occurs, such as during a particular task or when using a certain fabric or thread material. These situations can also be identified by an increase in heat generated by machine components and a corresponding rise in the temperature of certain components. More importantly, the sensors used in sewing machines are significantly more sensitive to changes in sounds or other parameters generated by sewing machine components, thus allowing for earlier predictions than other possible predictions, such as those made by experienced maintenance technicians. Furthermore, these performance problems can be correlated with other information from the sewing machine, such as the sewing operations being performed when the performance problem was detected and identified. In this way, specific performance problems can be associated with the specific use of the sewing machine and provide engineers and maintenance technicians with information about this relationship to better identify the causes of repairs and improve future designs. Just like other data collected by sewing machines and generated by neural networks, the data can be sent to the cloud to be shared with other sewing machines to improve the training of neural networks for all sewing machines in the network.

[0121] Now refer to Figure 86The flowchart illustrates the various ways diagnostic information can be generated by the sewing machine and used by the user. When the sewing machine's computer's neural network identifies that the machine needs calibration, the event is recorded and the user is notified. The user can then be instructed to perform a specific task to correct the problem, such as removing the thread or moving the sewing machine to a harder table. After taking action, the sewing machine can be used normally while periodically performing diagnostics to see if additional corrective actions are needed. If the user does not take corrective action, the motor or other actuators can be calibrated to attempt to correct the problem. If calibration fails to correct the problem, the user can be notified, the event recorded, and a service request sent to a service provider. As preventative maintenance, calibration can also be set for the motor or other components every specific number of cycles. Calibration can also be performed when changing the thread used and the fabric used with it, or when performing any work on the sewing machine.

[0122] Once a potential problem is diagnosed, the sewing machine can notify the user of the problem in a variety of ways, as described in this disclosure. Specifically, the sewing machine can present the notification to the user via a user interface, a voice alert, speaking to the user via computerized voice, and / or sending an email to the user via a network connection. For example, as... Figure 87 As shown, the sewing machine can present the user with instructions indicating that maintenance is needed and prompt the user to schedule a service request with the service dealer. Alternatively, as... Figure 88 As shown and described in more detail below, sewing machines can suggest changes to their operating environment to improve their performance. When changes or modifications to the operating environment are deemed necessary or recommended, reminders and guiding illustrations, animations, and videos can be presented to the user on a touchscreen or through localized guiding lighting or 2D or 3D static or dynamic light projection. These can guide the user by changing their working environment to reduce vibration, such as placing the sewing machine on a harder surface, or by instructing the user on simple repairs, or by guiding a technician on complex machine repairs.

[0123] For software issues, updates can be installed automatically without the user's knowledge. Alternatively, users can be guided through the software update process and provided with a user interface to contact customer service for support and correction. (See now for more information.) Figure 99An exemplary flowchart illustrating the use of a neural network with automatic software updates, as described above, is shown. When the sewing machine is not used for a predetermined period of time, i.e., when the user is inactive, data can be collected from user interaction or activity logs, user-facing cameras and microphones, a network interface connected to a software update server, and a clock providing the current date and time. If a software update is available, the neural network provides an indication of whether the user typically leaves the sewing machine for a sufficiently long time during the day to install the software update before the user returns to the machine. If sufficient time has passed, and if the user has enabled automatic updates, the software update is allowed to be installed. A similar process can be followed to calibrate various sensors, motors, actuators, etc.

[0124] Sewing machines may also include light sources, such as light-emitting diode (LED) lights, placed near various components known to wear out during use. These lights (e.g., yellow, orange, or red) can then illuminate specific components to indicate performance degradation that may require repair or replacement. When the machine is in maintenance or repair mode, these lights can be activated and provide a quick picture of the machine's overall health.

[0125] Health-related information about the sewing machine can be stored in a health log and transmitted to remote customer service representatives or service technicians to help remote workers determine what maintenance (if any) the machine may need and whether it needs to be sent to a service center for repair. With the user's permission, the sewing machine's health data can also be automatically sent to dealers, service centers, and / or manufacturers so that data recipients can take proactive steps to order replacement parts and notify the customer that specific components of the sewing machine may soon need replacement. In a commercial environment, sewing machine owners can choose to subscribe to a maintenance plan in which such replacement parts are delivered or service calls are automatically scheduled to keep the sewing machine up to a specific uptime.

[0126] Historical data recorded in the health log is particularly useful when diagnosing the cause of sewing machine malfunctions. For example, historical temperature data can include ambient temperature readings and temperature readings at various points within the machine. Ambient temperature history can show that the sewing machine has been exposed to an overheated environment that damaged it. Point temperature readings, i.e., temperature readings at specific locations within the sewing machine, can help technicians determine the root cause of the damage, such as wear and tear between damaged components. Historical vibration or acceleration data can be used similarly. Acceleration data can also indicate whether the machine has experienced a drop or fall, which could be the cause of the damage.

[0127] As described above, optical sensors can be used in conjunction with neural networks to detect when a user's finger or other foreign object may obstruct the sewing head and potentially cause injury to the user or damage to the machine. Similarly, neural networks can be trained to identify whether a user's finger or other foreign object obstructs the presser foot, cutting fitting, or any other moving component of the sewing machine that may cause injury to the user during machine use. When a finger or other foreign object is detected, the sewing machine can control the needle and other components to avoid the object, or if it is unavoidable or the potential harm is sufficient to prohibit further operation of the sewing machine, it can prevent further sewing. For example, when a finger is detected under the presser foot, the sewing machine can prevent the presser foot from descending. Or, when a finger or the user's hand is detected in the sewing path, the sewing machine can prevent further sewing. If the detected foreign object is a pin inserted into the seam, the sewing machine can adjust the feed rate or other sewing parameters to prevent the needle from hitting the pin.

[0128] The neural network can also consider the sewing machine's orientation (via accelerometers and / or pressure sensors on the base) to shut it off or prevent it from starting if it tilts enough to tip over and potentially injure the user. The accelerometer can also be activated when the sewing machine is in sleep or standby mode to detect movement and disable power to the machine if it is moved, picked up, or tipped over. Heat data from temperature sensors can be fed into the neural network so the machine can automatically shut down to prevent components from overheating or as a sign of potential electrical malfunction due to heat buildup.

[0129] User-facing proximity sensors (such as infrared sensors) and / or cameras can be used to monitor the presence of a user on the sewing machine so that it can automatically shut off after the user leaves for a predetermined time, saving energy. These user-facing sensors can also prevent the sewing machine from starting after an unauthorized person is identified attempting to access it via neural networks or other means. For example, a neural network can be trained to identify a child attempting to access the sewing machine. In response, the computer can prevent the sewing machine from activating and notify an authorized user of the attempted access by generating an audible sound or sending a notification to the user via an internet connection, text message, or smartphone application. An example flowchart of a child safety function is shown below. Figure 98As shown. Child safety analysis can be triggered for various reasons, such as after a failed attempt to access the sewing machine, or when a user might want to leave the sewing machine during a long embroidery process. Data is then collected from user-facing cameras, microphones, and various user interface elements such as touchscreens, buttons, and knobs. If the neural network determines that a child is attempting to access the sewing machine or is approaching an operating component of the sewing machine, the sewing machine can issue an audible alert and send a reminder to the mobile device assigned to the authorized user. If the child does not respond to the alert, the sewing machine can repeat the alert and stop the sewing operation to prevent injury. If the neural network determines that the unsuccessful attempt was not made by a child, the sewing machine can still issue an audible alert and send a message to the authorized user. As another example, the sewing machine can periodically monitor the environment around the sewing machine to identify the presence of people such as users or children. For example, such periodic monitoring can be performed when a child is too close to the ongoing sewing operation during a long embroidery process, which could potentially damage the embroidered work or cause injury. If a child is detected, the sewing operation can be stopped, and an alert can be sent to the user to notify them that the sewing operation has stopped and the reason for the stop.

[0130] When using a sewing machine, user settings such as profile settings, user preferences, graphical user interface settings, feedback settings, object recognition preferences, and tutorial preferences are monitored and stored. In addition to machine settings, every interaction between the user and the sewing machine can be recorded and stored. By processing the dataset related to user-machine interactions through neural networks, the sewing machine can learn user preferences to interact with the machine and predict user preferences in new situations. That is, setting changes can be related to items detected by the sewing machine or provided by the user, such as stitch type, thread type, and material type. This data collection allows the sewing machine to assist the user, for example, by suggesting feed rate settings for stitches the user has never sewn before, based on the characteristics of new stitches and the feed rates the user has set for other stitch patterns. As another example, the sewing machine can remind the user of settings typically set in the given current context; that is, by suggesting a specific feed rate or sewing pitch for thinner materials and a different feed rate or sewing pitch for thicker materials. An exemplary workflow using neural networks to recommend setting changes is as follows: Figure 97As shown. When settings are changed, data is collected from user interaction logs, current real-time interactions with the user, other sensors, neural networks about sewing materials, and data related to the current sewing operation. If the neural network identifies that the user typically makes the same changes in similar situations, the sewing machine prompts the user to decide whether the default settings should be changed. If the setting changes are not typically made in similar situations, the sewing machine can prompt the user to confirm that the change was intentional. Furthermore, the neural network can identify other settings that might typically be changed in similar environments and suggest these other changes to the user.

[0131] The sewing machine can also suggest that users take breaks or exercise periodically while using the machine to improve their ergonomic health. The suggested times, types of exercise, and rest periods are based on analysis of machine usage by a neural network trained to monitor user health. User posture can also be detected through neural network analysis of data from one or more user-facing cameras, allowing for further customization of exercise suggestions to benefit the user.

[0132] Sewing machines can also detect the conditions of the user's workspace and analyze them using neural networks. Ambient light sensors allow the neural network to consider the lighting conditions of the sewing machine's room and workspace to reduce or minimize contrast between the work area and the room. For example, the sewing machine can suggest brightening the room lights to reduce eye strain caused by the contrast between the sewing machine's bright work surface and the dark room. The sewing machine can also connect to the workspace and room lighting systems, for example, via a wireless (Wi-Fi) network, to automatically manage brightness adjustments. A user-facing camera can be used to determine the height of the work surface, the position of the user's chair, and other environmental conditions. When the sewing machine can approach an actively controlled surface, such as a height-adjustable workbench, it can suggest and adjust to improve the ergonomics of the work environment. Figure 103 An exemplary flowchart is shown, demonstrating how a sewing machine can reduce user stress by monitoring the environment around the machine. During sewing machine use, data collected from accelerometers, photoelectric sensors, user-facing cameras, and historical logs from previous sessions can be processed by a neural network to identify user health issues. For example, the neural network can identify if a user tends to sit in poor posture and can suggest changes, such as adjusting the user's chair. The neural network can also identify whether the work surface is unstable by monitoring vibration and acceleration data and suggest adjustments to the work surface to make it level and less prone to movement during sewing machine use.

[0133] As mentioned above, data collected by various sensors on the sewing machine and data generated by monitoring the machine's usage can be stored in the machine's database and transmitted to remote servers. Data transmitted to these remote servers can be collected into a central database and used to analyze sewing machine performance and user sewing behavior across a larger dataset. This so-called "big data" analytics can reveal patterns that are undetectable in smaller datasets. The results of this analysis can be fed back into the sewing machine's neural network or a remote neural network, which operates to support the machine's operation, thereby improving the quality of the results determined by the neural network. Big data analytics can also help R&D teams improve factory quality control processes and testing of various components in a laboratory environment. For example, failure modes that might not be predictable during the initial development of the machine can be identified through big data analytics, and these modes can be adapted to change parts and processes in future generations.

[0134] While various inventive aspects, concepts, and features of this disclosure may be described and illustrated in combination in exemplary embodiments, these different aspects, concepts, and features may be used individually or in various combinations and sub-combinations in many alternative embodiments. Unless expressly excluded herein, all such combinations and sub-combinations are within the scope of this application. Furthermore, although various alternative embodiments relating to various aspects, concepts, and features of this disclosure may be described herein, such as alternative materials, structures, configurations, methods, apparatuses and components, alternatives regarding shape, fit, and function, such description is not intended to be a complete or exhaustive list of available alternative embodiments, whether currently known or developed hereafter. Those skilled in the art will readily adopt one or more aspects, concepts, or features of the invention into other embodiments and uses within the scope of this application, even if such embodiments are not expressly disclosed herein.

[0135] Furthermore, although certain features, concepts, or aspects of this disclosure may be described herein as preferred arrangements or methods, such descriptions are not intended to imply that such features are necessary or essential unless explicitly stated otherwise. Additionally, exemplary or representative values ​​and ranges may be included to aid in understanding this application; however, these values ​​and ranges should not be construed as limiting and are only critical values ​​or ranges where such explicit statements are made.

[0136] Furthermore, while various aspects, features, and concepts may be explicitly identified herein as having inventive step or forming part of the disclosure, such identification is not intended to be exclusive, but rather may exist in aspects, concepts, and features that are fully described herein but are not explicitly identified as such or as part of a particular disclosure, which is instead set forth in the appended claims. The description of exemplary methods or processes is not limited to including all steps necessary in all cases, and the order in which steps are presented is not construed as necessary or essential unless explicitly stated otherwise. The words used in the claims have their full ordinary meaning and are not limited in any way by the description of the embodiments in the specification.

Claims

1. A method for calibrating one or more optical sensors on a sewing machine, the method comprising: Data is collected on one or more features of one or more predefined areas of at least one sewing machine, the environment surrounding the sewing machine, and sewing material, wherein the data is collected by at least one of one or more optical sensors; The data is processed by one or more neural networks, wherein the one or more neural networks detect and identify one or more features of one or more predefined regions from the data; Calculate one or more accuracy metrics for one or more features from the data, compared to one or more training features from one or more neural networks. Compare the values ​​of one or more accuracy metrics to one or more metric thresholds; as well as The parameters of at least one optical sensor among one or more optical sensors are adjusted based on a comparison between one or more accuracy metrics and one or more metric thresholds.

2. The method according to claim 1, wherein, If the value of one or more accuracy metrics is less than one or more metric thresholds, the method further includes collecting additional data on the feature, processing the additional data through one or more neural networks, calculating additional accuracy metrics, and comparing the value of the additional accuracy metrics with one or more metric thresholds.

3. The method according to claim 1, wherein, If the value of one or more accuracy metrics is greater than one or more metric thresholds, the method further includes setting one or more parameters of one or more optical sensors to an adjustment state based on a comparison between one or more accuracy metrics and one or more metric thresholds, as calibration parameters for one or more optical sensors.

4. The method of claim 1, wherein the method operates automatically at one or more of the following times: upon startup, during use of the sewing machine, and at any user-determined time point when the sewing machine is turned on.

5. The method of claim 1, wherein one or more predefined areas are located on a component or accessory of the sewing machine that is connected or loose thereto.

6. The method of claim 1, wherein one or more predefined areas are located on one or more of the needle bar, presser foot, presser foot ankle, needle plate, needle, paper or plastic sheet, or fabric.

7. The method of claim 1, wherein the data is visual data or image data associated with at least one of the geometry, color, contrast, or reflection of one or more predefined regions.

8. The method of claim 7, wherein the data is acquired from multiple images.

9. The method of claim 1, wherein one or more accuracy metrics include confidence probabilities of accuracy with respect to one or more features from the data.

10. The method of claim 1, further comprising sending an alarm signal or message requiring the user to ensure that one or more predefined areas are within the full field of view of one or more optical sensors.

11. A sewing machine, comprising: A sewing head, which is attached to an arm that is suspended above the sewing table via a support; A needle bar that extends from the sewing head to the sewing table, wherein the needle bar holds the needle; A presser bar, which has a presser foot, extends from the sewing head to the sewing table; One or more optical sensors are arranged to acquire data from one or more features of one or more predefined areas of the sewing machine; and One or more processors for processing data acquired by one or more optical sensors via one or more neural networks, wherein the one or more processors are configured to: Receive data from one or more optical sensors; Data is processed by one or more neural networks, wherein the one or more neural networks detect and identify one or more features of one or more predefined regions from the data; Calculate one or more accuracy metrics for one or more features from the data, compared to training features from one or more neural networks. Compare the values ​​of one or more accuracy metrics to one or more metric thresholds; and The parameters of at least one optical sensor among one or more optical sensors are adjusted based on a comparison between one or more accuracy metrics and one or more metric thresholds.

12. The sewing machine according to claim 11, wherein, If the value of one or more accuracy metrics is less than one or more metric thresholds, then one or more processors are also configured to acquire additional data for one or more features, process the additional data through one or more neural networks, calculate additional accuracy metrics, and compare the value of the additional accuracy metrics with one or more metric thresholds.

13. The sewing machine according to claim 11, wherein, If the value of one or more accuracy metrics is greater than one or more metric thresholds, then one or more processors are also configured to set one or more parameters of one or more optical sensors to an adjustment state as calibration parameters for one or more optical sensors based on a comparison between one or more accuracy metrics and one or more metric thresholds.

14. The sewing machine of claim 11, wherein one or more predefined areas are located on a component or accessory of the sewing machine that is connected to or loose therefrom.

15. The sewing machine of claim 11, wherein one or more predefined areas are located on at least one of the needle bar, presser foot, presser foot heel, needle plate, needle, paper or plastic sheet, or fabric.

16. The sewing machine of claim 11, wherein the data is visual data or image data associated with at least one of the geometry, color, contrast, or reflection of one or more predefined areas.

17. The sewing machine of claim 16, wherein the data is acquired from multiple images.

18. The sewing machine of claim 11, wherein one or more accuracy metrics include confidence probabilities of one or more accuracy parameters relating to one or more features derived from the data.

19. The sewing machine according to claim 11, wherein, If the value of one or more accuracy metrics is less than one or more metric thresholds, one or more processors are also configured to send an alarm signal or message requiring the user to ensure that one or more predefined areas are within the full field of view of one or more optical sensors.

20. The sewing machine according to claim 11, wherein, One or more neural networks are associated with a sewing machine and configured to share data with one or more additional neural networks associated with one or more different sewing machines or one or more parent neural networks in order to train the additional neural networks associated with one or more different sewing machines or one or more parent neural networks.

21. A sewing machine, comprising: The sewing head is attached to an arm that is suspended above the sewing bed by a support; A needle bar that extends from the sewing head to the sewing table, wherein the needle bar holds the needle; A presser bar, which has a presser foot, extends from the sewing head to the sewing table; One or more data acquisition devices associated with a sewing machine, arranged to acquire data from one or more features of one or more predefined areas of the sewing machine; and One or more processors for processing data acquired by one or more data acquisition devices via one or more neural networks, wherein the one or more processors are configured to: Receive data from one or more data acquisition devices; Data is processed by one or more neural networks, wherein the one or more neural networks detect and identify one or more features of one or more predefined regions from the data; Calculate one or more accuracy metrics for one or more features from the data, compared to training features from one or more neural networks. Compare the values ​​of one or more accuracy metrics to one or more metric thresholds; and The parameters of at least one data acquisition device in one or more data acquisition devices are adjusted based on a comparison between one or more accuracy metrics and one or more metric thresholds.

Images