Clothes processing device and control method thereof, computer equipment and storage medium

Abstract

The invention provides a clothes processing device and a control method thereof, computer equipment and a storage medium, the clothes processing device is equipped with an image acquisition module, the image acquisition module is used for acquiring a door seal area image of the clothes processing device, and the method comprises the following steps: acquiring the door seal area image; processing and analyzing the door seal area image to identify whether clothes are clamped in a door seal gap; when it is recognized that the clothes are clamped, the clothes clamping releasing operation is executed. According to the invention, intelligent sensing and active intervention of the working condition of the anti-clamping clothes are realized, the user experience and safety are fundamentally improved, the technical limitations of traditional mechanical fool-proof and simple sensing are broken through, the accuracy and reliability of detection are remarkably improved, a graded and collaborative intelligent unclamping strategy is provided, efficient and flexible fault processing is realized, and the working efficiency of the anti-clamping clothes is improved. The service life of core parts of the equipment is prolonged, and the overall reliability of the product is improved.

Description

Technical Field

[0001] This invention relates to the field of clothing processing technology, and in particular to a clothing processing device and its control method, computer equipment and storage medium. Background Technology

[0002] During the use of a front-loading washing machine, it is a very common malfunction that clothes get stuck in the gap between the door seal (also known as the door seal ring or sealing ring) and the inner drum or door glass. This problem mainly occurs in two stages: first, when the user closes the door after loading clothes, and second, during the high-speed spin-drying operation of the washing machine.

[0003] In front-loading washing machines, clothing (especially cuffs, trouser legs, hems, or long strips of fabric) is easily caught in the annular contact gap between the rubber lip of the door seal and the front end of the stainless steel inner drum under the influence of gravity or centrifugal force. Small, lightweight items such as socks, handkerchiefs, and silk underwear are even more easily sucked into or caught in these narrow gaps due to their small size and soft texture.

[0004] Clothes getting partially stuck may prevent the door from closing completely, preventing the washing machine from starting. If this happens after the spin cycle has started, the stuck clothes will be violently swirling with the high-speed rotation of the inner drum, continuously and irregularly impacting the door seal and door glass, producing a noticeable "thumping" noise and vibration. This abnormal vibration not only severely wears down the door seal rubber, shortening its lifespan, but it can also directly cause the washing machine to trigger its protection mechanism due to detected severe eccentricity, forcibly interrupting the spin cycle, or even stopping and alarming, seriously affecting the user experience and the washing process.

[0005] The reasons for clothing getting stuck are complex and varied, mainly falling into two categories: the characteristics of the clothing itself and the condition of the equipment. Specifically, thin, long garments (such as scarves, shawls, and belts) and garments with ropes, drawstrings, or hoods (such as hooded sweatshirts and sweatpants) are easily thrown into the door seal gaps and become entangled under the tumbling of the drum or the washing of water. Small items of clothing (such as socks and underwear) are easily moved to the gaps by the water flow due to their small size. Some smooth fabrics (such as silk and synthetic fibers) may adhere to the door seal rubber due to electrostatic attraction and then be pulled in. Furthermore, after long-term use, the door seal rubber will naturally age, lose elasticity, wrinkle, or permanently deform, causing it to no longer fit tightly with the inner drum, creating abnormal gaps that make it easy for clothing to get stuck. Wear on the inner drum support bearings may cause the inner drum to move axially or radially, increasing the gap between it and the door seal. In addition, improper installation of the door seal ring or loose door hinges may also cause excessively large local gaps.

[0006] Currently, the industry and users mainly rely on the following methods to address this issue, all of which have significant limitations: Before closing or starting the machine, users visually inspect and manually push the clothes completely into the drum. This method relies entirely on user experience and attentiveness, and is easily overlooked in actual operation, failing to fundamentally solve the problem. Some products use optimized door seal lip shapes (such as adding guide ribs or changing the tilt angle) or add protective retaining rings at the inner drum opening. These passive designs can reduce the probability of jamming to some extent, but they cannot cope with all types of clothing and complex dynamic water flow environments, cannot identify jamming that has already occurred, and lack proactive handling capabilities. A few high-end models are equipped with pressure- or photoelectric door seal foreign object sensors that can alarm when the door is obstructed. However, their detection accuracy is low and reliability is insufficient; they cannot distinguish between clothes stuck and normal door-closing resistance, and they cannot monitor and intervene in real time after the spin-drying program starts, when jamming is newly generated due to centrifugal force. Current washing machine eccentricity protection mechanisms are post-event remedial measures. It only activates when severe vibration has occurred, the equipment has been subjected to abnormal loads, and clothing and door seals may be damaged. It is a passive shutdown after a failure occurs, rather than a preventative measure before a failure occurs or an active shutdown during a failure.

[0007] In summary, existing technologies generally suffer from deficiencies in detection, delayed judgment, and passive handling. Therefore, there is an urgent need for a solution that can accurately identify foreign objects stuck in the door seal during the washing machine's operating cycle and intelligently and proactively perform unblocking operations based on the stuck state, in order to fundamentally improve product reliability, safety, and user experience. Summary of the Invention

[0008] To achieve the above-mentioned objectives and other advantages of the present invention, a first objective of the present invention is to provide a control method for a garment processing device equipped with an image acquisition module, the image acquisition module being used to acquire images of the door sealing area of ​​the garment processing device, comprising the following steps: Obtain the image of the door sealing area; The image of the door seal area is processed and analyzed to identify whether there is clothing stuck in the gap of the door seal; When clothing is detected to be stuck inside, the clothing is unstuck.

[0009] Furthermore, the steps for processing and analyzing the image of the door sealing area include: The image of the door seal area is subjected to HSV color space conversion and adaptive threshold segmentation to enhance the edge contrast between the door seal and the clothing. Analyze motion features in image sequences based on optical flow methods, and / or identify the contours of foreign objects in images based on object detection models.

[0010] Furthermore, the target detection model is a YOLO model trained on a dataset, which contains sample images of various lighting conditions and clothing materials synthesized through a generative adversarial network.

[0011] Furthermore, the operation of untying the clothing includes a water-fluid agitation step for untying: The water inlet system of the garment processing device is controlled to perform spraying to raise the water level in the washing drum of the garment processing device; Adjust the motor drive mode of the clothing handling device so that the washing drum swings forward and backward at a preset low speed. The water flow generated by the low-speed oscillation impacts and carries away clothing caught in the gaps of the door seal.

[0012] Furthermore, the water flow agitation and unclamping step also includes: After the preset unclamping attempt time has elapsed, the door seal area image is captured again to determine whether the clothing has been successfully unclamped. If it is confirmed that the clothes have been untangled, control the drainage to lower the water level and resume the washing program at the original normal cycle.

[0013] Furthermore, when clothing is detected, the process also includes the following steps: Analyze the morphological characteristics of the foreign object stuck in the tub; wherein, the morphological characteristics of the foreign object include at least one of the stuck area of ​​the foreign object, the type of foreign object, and the connection relationship between the foreign object and the clothes inside the tub, and the type of foreign object includes independent small items, clothing parts, and long strips of fabric; Based on the jamming morphology characteristics, a corresponding unjamming operation is selected and executed from at least two preset unjamming strategies, wherein the water flow turbulence unjamming step is configured as a basic unjamming operation in the at least two unjamming strategies.

[0014] Furthermore, the lifting ribs of the garment handling device are equipped with a clamping device, and the step of selecting and executing the corresponding unclamping operation from at least two preset unclamping strategies includes: When the condition is determined to be a first type of stuck state, the water flow turbulence release step is executed; When the condition is determined to be a second type of jamming, a two-stage unclamping strategy is executed: the washing drum is controlled to rotate so that the clamping device moves to the vicinity of the clothing body connected to the foreign object, and then the clamping device is controlled to clamp the clothing inside the drum connected to the foreign object and perform a dragging action to pull the foreign object into the drum.

[0015] Furthermore, the first type of jamming state is defined as follows: the jamming area of ​​the foreign object is less than a threshold, the foreign object type is an independent small piece and the connection relationship is independent; The second type of stuck state is defined as: the foreign object is a piece of clothing or a long strip of fabric, and / or the foreign object is connected to the clothing inside the tube.

[0016] Furthermore, the pulling action of the clamping device is coordinated with the auxiliary low-speed rotation or oscillation of the washing drum.

[0017] Furthermore, during or after the process of selecting and executing the corresponding unclamping operation step from at least two preset unclamping strategies, images of the door seal area are continuously or re-acquired to determine whether the unclamping is successful; if successful, the normal washing program is resumed; if unsuccessful, the final security strategy, including shutdown and user alarm, is triggered.

[0018] Furthermore, the image acquisition module is a retractable camera installed inside the lifting rib of the clothing processing device; prior to the step of acquiring the image of the door sealing area, the following is also included: The washing drum of the garment processing device is rotated to move the lifting rib to the preset shooting area; Control the camera to extend from inside the lifting rib to acquire images; After the data acquisition is completed, the camera is retracted into the lifting rib.

[0019] A second objective of the present invention is to provide a garment processing apparatus, comprising: An image acquisition module, which is mounted on the door glass or lifting rib of the clothing processing device, is used to acquire images of the door sealing area; The main control unit is configured to execute the above method.

[0020] Furthermore, it also includes a clamping device, which is assembled to the lifting rib.

[0021] A third objective of the present invention is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0022] A fourth objective of the present invention is to provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the above-described method.

[0023] Compared with the prior art, the beneficial effects of the present invention are: This invention provides a garment handling device and its control method, achieving intelligent sensing and proactive intervention in anti-clogging conditions, fundamentally improving user experience and safety. Within the operating cycle of the garment handling device, a closed-loop intelligent solution path is constructed for garments caught in the door seal. Through image acquisition and intelligent analysis, it can automatically and in real time identify garment-catching conditions that are easily overlooked by humans or undetectable by traditional sensors, and immediately trigger the corresponding unclogging procedure. This completely changes the passive situation where users need to handle faults afterward, avoiding program interruptions, garment damage, and even safety hazards caused by garment catching, providing a worry-free, intervention-free washing experience.

[0024] This invention overcomes the limitations of traditional mechanical error prevention and simple sensing technologies, significantly improving the accuracy and reliability of detection. Compared to passive protection measures such as optimizing door seal shape, this invention adopts a vision-based active sensing solution, which can adapt to different clothing materials, shapes, and jamming angles, making it highly versatile.

[0025] This invention extends the service life of the core components of the equipment and improves the overall reliability of the product. Abnormal friction and impact between the door seal and the inner drum are the main causes of premature aging and damage. This invention effectively prevents continuous impact and wear on the door seal during high-speed spin-drying by timely detection and release of obstructions, while also avoiding the risk of damage to the inner drum bearings due to long-term abnormal stress. This fundamentally reduces maintenance needs caused by such failures and lowers the total life cycle cost of the product.

[0026] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, the preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings. Specific embodiments of the present invention are given in detail below with reference to the accompanying drawings. Attached Figure Description

[0027] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings: Figure 1 A flowchart of the control method for a garment handling device; Figure 2 This is a cross-sectional view of the garment processing device; Figure 3 To improve the image acquisition module acquisition control flowchart; Figure 4 Flowchart for image processing and analysis of the door sealing area; Figure 5 Flowchart for unwinding water flow turbulence; Figure 6Flowchart for verifying the effectiveness of untangling clothing in turbulent water flow; Figure 7 A flowchart of hierarchical unclamping process based on jamming morphological characteristics; Figure 8 A flowchart for selecting and implementing flexible flushing and mechanical intervention based on the complexity of clothing jamming; Figure 9 This is a schematic diagram of a computer device. Figure 10 This is a schematic diagram of a computer-readable storage medium.

[0028] In the diagram: 1. Image acquisition module; 2. Door seal; 3. Washing drum; 4. Lifting rib; 5. Telescopic drive mechanism; 6. Door glass. Detailed Implementation

[0029] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. It should be noted that, without conflict, the various embodiments or technical features described below can be arbitrarily combined to form new embodiments.

[0030] Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of this invention.

[0031] The drawing numbers in this application are only used to distinguish the steps in the scheme and are not used to limit the execution order of the steps. The specific execution order is as described in the specification.

[0032] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0033] In existing washing machine products, clothing getting stuck in the door seal area is a long-standing technical problem. This issue mainly manifests in the following typical phenomena: clothing (especially thicker areas like cuffs and trouser legs, or long strips of fabric like scarves) easily gets caught at the dynamic contact interface between the door seal ring and the inner drum. Simultaneously, small, thin items like socks and underwear are also very prone to getting stuck in this narrow gap. This type of jamming directly prevents the door from closing completely, preventing the washing machine from starting normally. When jamming occurs during the spin-drying stage, the stuck clothing continuously impacts the door seal assembly during high-speed rotation, producing periodic abnormal noises. This abnormal vibration not only accelerates door seal wear but also triggers the washing machine's eccentricity protection mechanism, causing abnormal interruptions to the spin-drying program, severely impacting washing efficiency and user experience.

[0034] Existing solutions include optimizing the geometry of the door seal lip or adding protective rings, but such passive protection cannot adapt to all types of clothing and cannot achieve real-time identification of jamming conditions. Contact sensors are used to detect closing resistance, but they cannot distinguish between normal closing resistance and clothing jamming, and they completely fail during the spin-drying stage. As a remedial measure, they only force a shutdown after abnormal vibration occurs, which is a passive response rather than proactive prevention. Existing solutions lack real-time monitoring of jamming conditions in the door seal area, cannot distinguish the type of jammed object or the severity of the jamming, and only provide simple responses such as door closing alarms or post-event shutdowns, lacking intelligent handling capabilities.

[0035] Therefore, there is an urgent need for a technical solution that can accurately identify the jammed state of door seals in real time and intelligently perform unblocking operations based on the jamming characteristics, so as to truly achieve a technological leap from passive response to proactive prevention.

[0036] The clothing processing equipment can be configured as a washing machine, a washer-dryer combo, etc. For ease of description, this invention uses a drum washing machine as an example for illustration, and should not be construed as a limitation on the type of clothing processing equipment.

[0037] This method can be executed by the main control unit of the garment processing device. The main control unit can be implemented in the form of software and / or hardware, and is generally integrated into any electronic device with network communication capabilities, such as a mobile terminal, PC, or server.

[0038] Example 1 A control method for a garment handling device, such as Figure 2 As shown, the garment processing device is equipped with an image acquisition module 1, which is used to acquire images of the door seal 2 area of ​​the garment processing device, such as... Figure 1 As shown, the method includes the following steps: S100: Obtain the image of the door sealing area; When it is necessary to detect whether clothing is caught in the door seal area, the image acquisition module is activated and supplementary lighting is turned on. For example, before and during the spin-drying process, images of the door seal area are continuously acquired at a certain frame rate (e.g., 10fps).

[0039] The image acquisition module can utilize a wide-angle waterproof camera, such as a 2-megapixel waterproof camera with a 120° wide-angle field of view. To obtain the optimal monitoring angle and balance installation and protection requirements, such as... Figure 2As shown, the camera can be selectively embedded in the door glass 6 (the camera is not shown here) or built into the lifting rib 4. Preferably, when the image acquisition module 1 is placed inside the lifting rib 4, a retractable structure can be adopted. To cope with the dim lighting environment inside the tube, the clothing handling device is also equipped with a supplementary lighting module (such as an LED downlight). This module can be triggered synchronously with the camera to provide uniform illumination during image acquisition, ensuring image quality.

[0040] Optionally, image processing can be performed by an edge computing module, such as using the Rockchip RK3588 chip. This module is directly deployed within the washing machine controller and is responsible for running the image recognition algorithm. Its processing latency can be controlled within 150 milliseconds, meeting real-time requirements. To reduce overall power consumption, an event-triggered wake-up mechanism is also adopted: during non-spinning stages or when there is no significant risk, the image acquisition module and processing module are in a low-power standby state, with power consumption below 0.5W; when entering the spin-drying stage or other preset trigger conditions (such as after the door is closed or before high-speed rotation) are met, they are woken up and enter full-function working mode, acquiring image data collected by the image acquisition module through the edge computing module's interface, and then performing image processing, etc.

[0041] In some embodiments, the image acquisition module is a retractable camera disposed inside the lifting rib of the clothing processing device; to ensure that the retractable camera can obtain the best field of view of the door sealing area when extended, facilitating subsequent high-precision image recognition. Figure 3 As shown, the method further includes the following steps before the step of acquiring the image of the door sealing area: S110. Control the washing drum of the clothing processing device to rotate so as to drive the lifting rib to the preset shooting area; Because the lifting ribs are distributed circumferentially along the inner drum wall, when the lifting ribs equipped with retractable cameras rotate to different circumferential positions with the washing drum, the observation angle and line of sight of the cameras will change significantly due to the relative position of the washing drum geometry and the door seal.

[0042] Because the lifting rib is located at or near the bottom, its view may be obstructed by the structure of the washing drum itself (such as the drum wall, dehydration holes) or other lifting ribs, making it impossible to obtain a clear and comprehensive direct view of the door seal gap. Through experiments and simulations, it has been verified that when the lifting rib equipped with the camera rotates to the top area of ​​the inner drum circumference (e.g., a fan-shaped range of ±30° to ±60° relative to the vertical line), as... Figure 2 As shown, the camera has optimal observation conditions, with an unobstructed line of sight directly reaching the contact gap area between the door seal 2 and the front edge of the washing drum 3. It is easier to obtain uniform illumination from the supplementary light, reduce shadows, and maximize the use of the lens's depth of field to ensure clear imaging of the door seal plane.

[0043] Therefore, before extending the camera to acquire key images, the lifting rib must first be positioned in the top area. Optionally, the washing machine's main control unit uses a motor encoder or a dedicated Hall position sensor to obtain the absolute angular position of the washing drum and the lifting rib in real time, and knows the fixed installation offset angle of the lifting rib with the camera mounted on it on the inner drum circumference, to calculate whether the current camera lifting rib is already in the preset top image acquisition area.

[0044] S120: Control the camera to extend from the lifting rib to acquire images; In order to control the camera, such as Figure 2 As shown, the lifting rib 4 is also equipped with a telescopic drive mechanism 5, which includes a drive source and a transmission mechanism. Optionally, a miniature, high-torque stepper motor or a miniature linear motor is selected as the power source, and a cam-linkage combination mechanism is used to achieve precise linear telescopic motion. The rotating output shaft of the motor is connected to a cam with a specific profile. The profile surface of the cam contacts one end of a driven link, and the other end of the link is rigidly connected to the camera support platform through a slide rail. When the motor rotates to the first angle, it pushes the link to put the camera in the fully retracted storage position; when the motor rotates to the second angle, it smoothly pushes the camera out to the working position.

[0045] Once the camera extends to the optimal shooting position, it immediately begins capturing images. Because the field of view is optimal, the image quality is highest at this point, which is beneficial for making the most accurate judgments based on the image.

[0046] S130. After the data acquisition is completed, control the camera to retract into the lifting rib.

[0047] After the camera retracts into its original position, the main control unit releases the forced constraint on the position of the lifting ribs, allowing the washing drum to rotate freely to any desired position as needed for the washing or spin-drying process.

[0048] Optionally, during the preparation phase before the dehydration process begins, or during the first stable period after high-speed dehydration, the main control unit automatically triggers a camera extension command as a preventative monitoring measure. Alternatively, when the vibration sensor detects an abnormal impact, or the current sensor detects a sudden load change, the main control unit immediately triggers an emergency camera extension command.

[0049] S200. Process and analyze the image of the door seal area to identify whether there is clothing stuck in the door seal gap; In some embodiments, such as Figure 4 As shown, the steps for processing and analyzing the image of the door sealing area include: S210. Perform HSV color space conversion and adaptive threshold segmentation on the door seal area image to enhance the edge contrast between the door seal and the clothing. After acquiring the original RGB image of the door seal area, preprocessing is performed to optimize subsequent analysis. Specifically, the RGB image is converted to the HSV (Hue, Saturation, Value) color space. Since the rubber material of the door seal (usually black or dark gray) typically differs significantly from various types of clothing in hue and saturation, this conversion helps to separate color information from brightness information.

[0050] Then, adaptive thresholding is performed, focusing on the brightness (V) channel, as edge information is primarily contained therein. The Otsu method or local adaptive thresholding is used, dynamically calculating the segmentation threshold based on the brightness distribution of different areas of the image, rather than using a fixed threshold. This effectively addresses the uneven lighting issues caused by curved surface reflections and water droplets in the door seal area. Through thresholding, a binarized image is obtained, where the door seal rubber (darker area) and potential foreign objects (brighter area) are significantly distinguished, enhancing edge contrast and laying the foundation for contour extraction. It should be noted that in this embodiment, the foreign object refers to an object relative to the structural components of the door seal / washing drum or other clothing handling device in the image. In the specific application scenario of this embodiment, the foreign object refers to clothing trapped in the gap between the door seal and the washing drum / door glass.

[0051] S220. Analyze motion features in image sequences based on optical flow and / or identify the contours of foreign objects in images based on target detection models.

[0052] Preferably, the target detection model is a YOLO model trained on a dataset, which contains sample images of various lighting conditions and clothing materials synthesized through a generative adversarial network.

[0053] To balance real-time performance and accuracy, a hybrid strategy integrating traditional image processing and deep learning is adopted. Motion feature analysis based on optical flow specifically involves calculating the motion vector (velocity and direction) of each pixel or feature point in a continuously acquired image sequence (e.g., 10 frames per second) using either the Farneback dense optical flow algorithm or the LucasKanade sparse optical flow algorithm. A normal optical flow pattern in the door seal area during uniform drum rotation is established as the background. The current optical flow field is analyzed; if a group of stationary points significantly inconsistent with the drum's rotation direction, a small area with periodic reciprocating oscillations (matching the spin-drying impact frequency), or an isolated area with violently disordered motion is detected in the door seal area, it is determined that the area exhibits abnormal motion patterns such as periodic jamming vibrations, which are typical characteristics of clothing being caught and swung by the drum. This method is not sensitive to color or texture and is particularly effective for targets that are difficult to segment by color, such as dark clothing and semi-transparent stockings.

[0054] The morphological recognition based on the object detection model specifically involves: employing the lightweight and efficient YOLOv5 object detection model and optimizing its deployment on the NPU of the edge computing module for real-time inference. Its core training data includes a large number of images of clothing clipped to door seals in real-world scenarios, with precise bounding boxes annotated with clothing outlines. To improve the model's robustness in complex environments, a Generative Adversarial Network (GAN) is used to augment the original dataset, synthesizing samples with the following diversity: simulating reflections caused by strong sidelight, shadows caused by backlighting, and low light at night; synthesizing water droplets on glass, residual foam, and stains on door seals; and covering clothing with different textures and reflective properties, including dry / wet cotton, linen, silk, and synthetic fibers. Through this data augmentation, the model achieves extremely strong generalization ability, maintaining high accuracy even in complex scenarios in practical applications.

[0055] Optionally, the specific process of synthesizing training samples using GAN is as follows: A CycleGAN or StyleGAN2 network structure is used as the basic framework; the input source consists of labeled normal doorway images (i.e., the source domain) and a small number of images containing various target characteristics (such as images of strong light reflections, water droplets, and close-up images of clothing of various materials, i.e., the target domain); the GAN is trained to learn the style mapping from the source domain to the target domain. For example, it learns to transform a doorway under normal lighting into a doorway with strong glass reflections, while maintaining the structure of the doorway and clothing. Using the trained generator, images from the original dataset are synthesized in batches into various simulated environments, thereby constructing a large training dataset covering long-tailed scenes at low cost and high efficiency.

[0056] In real-time detection, the preprocessed door seal area image is input into the YOLOv5 model, and the model outputs the bounding boxes, category confidence, and contour information of all suspected clothing in the image.

[0057] Optionally, the final judgment can be made by combining the above analysis results. If the optical flow method identifies an abnormal motion pattern and the YOLOv5 model detects a high-confidence foreign object outline in the same area, it is confirmed that clothing is trapped, with the highest confidence level. If only the YOLOv5 model detects a high-confidence outline, but the optical flow analysis shows no abnormalities (this may occur before dehydration or at low speed), it is still determined that clothing is trapped, but it is marked as static jamming. If only the optical flow analysis shows an abnormality but the model does not detect a clear outline (possibly because the color of the clothing is extremely similar to the background), the system triggers a suspicious alarm, and can control the camera to zoom or adjust the supplementary light before re-detecting, or combine the vibration sensor signal for a comprehensive judgment.

[0058] S300: When clothing is detected to be stuck inside, perform the operation to untie the clothing.

[0059] When clothing is confirmed to be trapped in the door seal gap (especially if it is identified as a small, independent foreign object or slightly stuck), the main control unit interrupts the current standard spin-drying program and initiates the following intelligent untrap process. In some embodiments, such as Figure 5 As shown, the operation of untangling clothing includes the step of using water to agitate and untangle the clothing: S310. Control the water inlet system of the garment processing device to perform spraying to raise the water level in the washing drum of the garment processing device; Specifically, the main control unit sends control commands to the water inlet system. Depending on the configuration of the laundry handling unit, one or a combination of the following methods is selected to quickly raise the water level: 1. Control the spray inlet valve to open, using the water supply line pressure to spray water into the washing drum in a parabolic or diffused pattern. This method provides a fast water inlet speed and quickly creates water flow disturbance. 2. Start the circulating water pump to pump up the water stored at the bottom of the washing drum and re-spray it through the spray nozzles to the upper part of the drum and the door seal area. This method is highly efficient when there is already a certain amount of water at the bottom and promotes water circulation.

[0060] The target water level here is not the high water level of a standard wash, but rather a set agitation water level. This level is higher than the low water level during spin-drying, but lower than the standard wash water level. Preferably, the agitation water level is set so that the water surface is slightly below the rotation axis of the washing drum's leading edge, ensuring that the water flow can adequately reach the door seal gap area during subsequent low-speed oscillations, while avoiding excessive water volume that could overload the system. The main control unit monitors the water level in real time via a water level sensor and shuts off the water supply once the target water level is reached.

[0061] S320. Adjust the motor drive mode of the clothing processing device so that the washing drum swings forward and backward at a preset low speed. Specifically, the main control unit switches the drive motor's control mode from high-speed spin-drying rotation to low-speed oscillation mode. For example, the control roller operates at a low speed between 120 rpm and 180 rpm. This speed range has been verified through fluid dynamics simulation and experiments: too low a speed results in insufficient water kinetic energy and weak scouring force; too high a speed may cause the water flow pattern to change from turbulence to rotation, reducing the directional scouring effect on gaps and potentially causing clothes to become more tightly entangled. Alternating forward and reverse oscillations of preset duration are used. For example, rotating forward for 3 seconds, pausing for 0.5 seconds, rotating backward for 3 seconds, pausing for 0.5 seconds, and so on. The brief pauses help to abruptly change the water flow direction, generating stronger turbulence and impact force. The total duration can be preset, or it can form a closed loop with subsequent detection steps.

[0062] S330: Through the turbulent water flow generated by low-speed oscillation, it impacts and carries away clothing caught in the gaps of the door seal.

[0063] During this stage, the slow-moving roller causes the water inside the drum to undergo violent reciprocating motion, creating a powerful turbulent water flow. This water flow, at a certain speed and angle, directly impacts clothing stuck in the door seal gaps, attempting to push or wash it away from the physical gaps. The reciprocating motion of the water creates periodic pressure changes at the gaps, helping to loosen the tightly stuck clothing fibers. The turbulent water flow keeps the clothing inside the drum in a loose, tumbling state, helping to separate the stuck clothing from the door seal and bring it into the main space inside the drum.

[0064] To verify the effectiveness of unsnagging clothing, such as Figure 6 As shown, the water flow turbulence unclamping step further includes: S340. After the preset unclamping attempt time has been reached, the door seal area image is captured again to determine whether the clothing has been unclamped. Optionally, during the execution of the oscillation program or after the preset total duration is reached, the main control unit pauses the swing of the washing drum, sends an instruction to the image acquisition module to acquire the image of the current door seal area again, and then calls the above image processing and analysis process to process the acquired new image, analyze the area that is the same as the previously recorded jamming position, and determine whether the foreign object outline in the area has disappeared and whether the abnormal optical flow mode has returned to normal.

[0065] If the image analysis results show that the confidence level of the foreign object contour in the target area is below a very low threshold (e.g., <5%) and there are no abnormal motion features, it is determined that the clothing has been successfully unstuck.

[0066] If the outline of the foreign object is still clearly discernible (confidence level > 50%) or the abnormal movement characteristics continue, it is determined that the unclamping was unsuccessful.

[0067] If the test result is in an intermediate state, the main control unit can choose to extend the oscillation time (e.g., execute for another 5 seconds) and then verify again, or directly upgrade the processing scheme according to the preset strategy.

[0068] S350: If it is confirmed that the clothes have been untangled, control the drainage to lower the water level and restore the washing program to the original normal cycle.

[0069] If image analysis confirms that the foreign object in the door seal gap has disappeared, the unclamping is considered successful. The main control unit stops the washing drum from oscillating, shuts off the water inlet system (if water is still inlet), and starts the drainage program (i.e., immediately starts the drain pump or opens the drain valve) to lower the water level to the target level. The target drainage level is the water level required for the next stage of the original washing program. For example, if the water turbulence program is triggered before the spin-drying stage, the water level needs to be drained to the low or zero level required for spin-drying, and then the normal spin-drying program is restarted, continuing from near the interruption point; if the water turbulence program is triggered during the rinsing stage, it may need to be drained to the water level required for the next rinsing or spin-drying stage. Feedback from the water level sensor ensures that the water level accurately reaches the target value.

[0070] After the water level is lowered to the target level, the main control unit switches the control mode of the drive motor from low-speed forward and reverse oscillation back to the normal rhythm at the time of the original program interruption. For example, if the interruption occurred during the dehydration stage, it will resume high-speed unidirectional rotation (e.g., 800 rpm or higher); if the interruption occurred during the rinsing stage, it will resume the standard rinsing oscillation rhythm (e.g., forward and reverse rotation at a specific speed).

[0071] The control system resumes operation from the logical node (rather than a strict point in time) where the program was interrupted. For example, it records the execution time of dehydration or rinsing when the interruption occurred and makes up the remaining time after the program resumes; or it directly proceeds to the next preset program step.

[0072] Clear all abnormal flags triggered by the clothing clipping incident and restore the image monitoring system to regular inspection or low-power standby mode.

[0073] If the clothing is still stuck, the agitation can be repeated depending on the severity of the sticking. The parameters can be adjusted (such as slightly increasing the water level or changing the swing rhythm) to execute another round of water agitation.

[0074] If the problem persists after repetition, or if the initial identification indicates severe jamming (such as a large area of ​​clothing being caught), a higher-level unclamping strategy is triggered, such as controlling the clamping device within the lifting rib to perform physical intervention.

[0075] As a last resort, if all unblocking measures fail, all actions will be stopped immediately, the door will be locked, and a clear alarm will be issued to the user via sound, light, and APP push notifications, prompting manual handling.

[0076] The water flow turbulence unclamping method provided in this embodiment achieves non-contact, flexible, and proactive unclamping of clothes. It makes full use of the existing water inlet and drainage system and drive system of the washing machine, without the need for complex additional mechanisms. Through intelligent control software algorithms, it effectively solves common clothes clamping problems while protecting the clothes and the machine itself to the greatest extent, demonstrating a high degree of intelligence and practicality.

[0077] The solution provided in this embodiment not only proactively attempts to resolve problems but also autonomously verifies the effectiveness of the solutions and seamlessly resumes the washing program. This avoids the drawbacks of traditional methods, which either run ineffectively for extended periods or simply stop and wait for the user. It truly achieves fully automatic and highly reliable fault handling, greatly enhancing the user experience and the product's autonomous and intelligent image.

[0078] To achieve refined, personalized, and adaptive processing of clothing jamming problems of varying complexity, when clothing is detected, such as... Figure 7 As shown, it also includes the following steps: S360. Analyze the jamming morphological characteristics of the foreign object; wherein, the jamming morphological characteristics include at least one of the jamming area of ​​the foreign object, the type of foreign object, and the connection relationship between the foreign object and the clothing inside the tube.

[0079] After confirming the presence of a stuck foreign object through image recognition, a more refined analysis of the stuck object's morphological features can be initiated. This analysis can be run on the edge computing module. Specifically, based on the foreign object's contour mask output by the target detection model, its pixel area is calculated. Combining camera intrinsic parameters and the known physical dimensions of the door seal gap (obtained through calibration), the pixel area is converted into an approximate actual physical area, or its percentage of the visible gap area of ​​the door seal is calculated.

[0080] By analyzing the geometric features of the outline (such as aspect ratio, roundness, and compactness) and the texture features extracted through a convolutional neural network, the system distinguishes whether the foreign object is an independent small item (such as socks or handkerchiefs, which are usually compact in shape), a piece of clothing (such as cuffs or trouser legs, which may appear as irregular pieces), or a long strip of fabric (such as scarves or ribbons, which have a significant aspect ratio). For example, if the aspect ratio of the outline is >3:1, it is judged to be long and narrow; if the area is less than a threshold and the shape is compact, it is judged to be an independent small item; otherwise, it tends to be judged to be a piece of clothing.

[0081] The connection between the foreign object and the clothes inside the drawer is crucial for determining the severity of the jamming. A retractable camera within the lifting rib can capture multi-angle images during the swinging motion. Feature matching algorithms (such as SIFT and ORB) or deep learning-based association detection models can then be used to analyze the relationship between the foreign object's outline at the door seal and other areas of clothing inside the drawer in terms of texture, color, and edge continuity. If a stable correspondence can be established between the foreign object at the door seal and a specific area of ​​clothing inside the drawer across multiple frames, the object is considered connected; otherwise, it is considered independent.

[0082] S370. Based on the stuck morphological characteristics, select and execute the corresponding unsqueezing operation from at least two preset unsqueezing strategies, wherein the water flow turbulence unsqueezing step is configured as a basic unsqueezing operation in the at least two unsqueezing strategies.

[0083] Based on the analysis results of the S360 steps, the stuck states are classified, and corresponding solutions are selected from a preset strategy library. In some embodiments, such as Figure 8 As shown, the lifting ribs of the garment handling device are equipped with a clamping device, and the step of selecting and executing the corresponding unclamping operation from at least two preset unclamping strategies includes: S371. When the first type of jamming state is determined, the water flow turbulence unblocking step is executed; wherein, the first type of jamming state (slight, independent) is defined as: the jamming area of ​​the foreign object is less than the threshold (such as occupying 10% of the visible area of ​​the gap), and it is identified as a small independent foreign object, that is, the foreign object type is an independent small piece and the connection relationship is independent.

[0084] At this point, the water flow turbulence release step should be performed first, as it is gentle, has a high success rate, and is suitable for this type of loose and stuck object.

[0085] S372. When the condition is determined to be a second type of jamming state, a two-level unclamping strategy is executed: the washing drum is controlled to rotate so that the clamping device moves to the vicinity of the main body of the clothing connected to the foreign object, and then the clamping device is controlled to clamp the clothing in the drum connected to the foreign object and perform a dragging action to pull the foreign object into the drum.

[0086] The second type of jamming state (complex, connected) is defined as follows: the foreign object is a part of clothing or a long strip of fabric, and / or the connection between the foreign object and the clothing inside the drum is connected, that is, the foreign object is part of a piece of clothing, and another part of the clothing is located inside the washing drum and connected to the foreign object. This type of jamming usually involves a large area or a firm connection.

[0087] In this state, mechanical intervention is initiated. First, the washing drum is rotated to move the gripping device to the vicinity of the main body of the clothing inside the drum that is connected to the foreign object. Then, the gripping jaws extend to stably hold the target clothing portion. While the jaws apply a stable pulling force, the washing drum is controlled to perform auxiliary low-speed rotation or small-angle oscillation (e.g., rotating 10-20 degrees per second in a direction conducive to release). This coordinated pulling method effectively amplifies the release force and avoids damage to the clothing caused by pulling in one direction.

[0088] In addition, the dragging action can be designed as an oscillating motion, that is, the grippers perform high-frequency micro-amplitude reciprocating motion while maintaining the clamping force, so as to more gently break the fiber entanglement.

[0089] Optionally, the clamping device integrates a pressure sensor to monitor the clamping force in real time. When the pulling force exceeds a preset safety threshold for clothing, the dragging stops immediately to prevent damage to the clothing.

[0090] This embodiment can automatically select and execute a progressive solution, from gentle rinsing to mechanical intervention, based on the complexity of the clothing jamming.

[0091] It should be noted that when the camera and clamping device are installed inside the lifting rib, the image needs to be transmitted to the processor via in-drum power supply technology, waterproof cable, or wireless module. This embodiment does not limit the specific implementation method of in-drum power supply; all solutions that can achieve in-drum power supply are applicable to this application. For example, the invention described in patent application CN202211607494.0, entitled "A Device for Powering the Inside of a Drum Washing Machine and a Washing Machine," and patent application CN2023116816837, also entitled "A Device for Powering the Inside of a Drum Washing Machine and a Washing Machine," etc.

[0092] This embodiment does not limit the specific implementation of the clamping device; all solutions integrated into the lifting ribs that can clamp clothes are included in this application. For example, Chinese Patent ZL202223339070.9 discloses a washing machine clothes clamping device based on light judgment results; and the clamping device described in the patent application with application number CN202410236754.0, entitled "A Washing Control Method and Washing Device That Can Automatically Hang Clothes".

[0093] During or after the execution of the corresponding unclamping operation step selected from at least two preset unclamping strategies, images of the door seal area are continuously or re-acquired to determine whether the unclamping is successful. If successful, the normal washing program is resumed; if unsuccessful, the final security strategy, including shutdown and user alarm, is triggered.

[0094] Specifically, during the execution of steps S371 or S372, the image acquisition module operates continuously at a low frequency to monitor the dynamic changes of the stuck area in real time. That is, after the execution of any level of strategy, it is necessary to re-acquire images of the door sealing area and perform precise analysis to ultimately verify whether the unblocking was successful.

[0095] If the verification is successful, the main control unit immediately resumes the normal washing program, including draining water to the appropriate level, restoring the original motor speed and rhythm, and seamlessly resuming from the interruption point.

[0096] If the highest level of unclamping strategy (such as secondary mechanical intervention) still fails to verify, the main control unit determines that it cannot handle the problem automatically and immediately triggers the final safety strategy. This includes immediately stopping the operation of all motors and pumps, and issuing an audible and visual alarm via panel indicator lights and a buzzer. At the same time, a strong reminder alarm is pushed to the bound smartphone APP via Wi-Fi / Bluetooth module. The alarm message may include: "Severe clothing jam detected, automatic unclamping failed, please handle manually," and may be accompanied by a clear image of the last detection to ensure that the door lock can be safely opened after the machine is completely stopped, making it convenient for the user to handle the problem.

[0097] For example, after mechanical intervention, the gripper is released and checked again. If the release is successful, the program continues; if it fails, the final safety strategy is triggered: the dehydration process is stopped immediately, and an alarm message and a captured image of the gripping area are pushed to the user's mobile app via the WiFi module.

[0098] This embodiment achieves refined, personalized, and adaptive handling of jamming problems of varying complexity. From non-contact water flow agitation to precise mechanical collaborative operation, and comprehensive safety safeguards, it maximizes user freedom while ensuring the safety and reliability of the processing.

[0099] This embodiment provides a control method for a garment handling device, achieving intelligent sensing and proactive intervention in anti-clogging conditions, fundamentally improving user experience and safety. Within the operating cycle of the garment handling device, a closed-loop intelligent solution path is constructed for clothing caught in the door seal. Through image acquisition and intelligent analysis, it can automatically and in real time identify clothing catching conditions that are easily overlooked by humans or undetectable by traditional sensors, and immediately trigger the corresponding unclogging procedure. This completely changes the passive situation where users need to handle faults afterward, avoiding program interruptions, garment damage, and even safety hazards caused by clothing catching, providing a worry-free, intervention-free washing experience.

[0100] This embodiment overcomes the technical limitations of traditional mechanical error prevention and simple sensing, significantly improving the accuracy and reliability of detection. Compared to passive protection measures such as optimizing the shape of the door seal, this embodiment adopts a vision-based active perception scheme, which can adapt to different clothing materials, shapes, and jamming angles, making it highly versatile. Compared to simple contact or photoelectric sensors, the image recognition method in this embodiment can not only determine whether there is a foreign object, but also further analyze what the object is and its jamming morphological characteristics (such as jamming area, type, and whether it is connected to the clothing inside the garment). This multi-dimensional state recognition provides a reliable basis for subsequent execution of differentiated and precise unblocking strategies, greatly reducing false alarms and false negatives.

[0101] This embodiment proposes a tiered and collaborative intelligent unclamping strategy, achieving efficient and flexible fault handling. Instead of simply triggering an alarm or shutting down the machine, this embodiment executes a tiered response strategy, ranging from hydraulic agitation to mechanical intervention, based on intelligent analysis of the jamming morphology. For example, for loose, small foreign objects, non-contact water jet flushing is prioritized to unclamp them, maximizing the protection of clothing; for tightly packed or connected jams, active intervention such as mechanical clamping is initiated. This collaborative handling mechanism, employing a combination of gentle and forceful approaches, efficiently resolves the problem while ensuring the protection of clothing and the machine itself, demonstrating a high degree of intelligence and human-centered design.

[0102] This embodiment extends the service life of the core components of the equipment and improves the overall reliability of the product. Abnormal friction and impact between the door seal and the inner drum are the main causes of premature aging and damage. This embodiment effectively prevents continuous impact and wear on the door seal during high-speed spin-drying by timely detection and release of jams, and also avoids the risk of damage to the inner drum bearings due to long-term abnormal stress. This fundamentally reduces maintenance needs caused by such failures and lowers the total life cycle cost of the product.

[0103] Example 2 Based on the same concept, this embodiment also provides a clothing handling device that applies the control method provided in Embodiment 1. A detailed description of the control method provided in Embodiment 1 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. In some embodiments, the clothing handling device can be applied as a washing machine, and in other embodiments as a washer-dryer combo.

[0104] It is understood that the garment processing device provided in this embodiment includes hardware structures and / or software modules corresponding to each function in order to achieve the above-mentioned functions. In conjunction with the units and algorithm steps of the various examples disclosed in this embodiment, this embodiment can be implemented in hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the technical solution of this embodiment.

[0105] A garment processing device, such as Figure 2 , Figure 3 As shown, it includes: An image acquisition module, which is mounted on the door glass or lifting rib of the clothing processing device, is used to acquire images of the door sealing area; The main control unit is configured to execute the above method.

[0106] When it is necessary to detect whether clothing is caught in the door seal area, the image acquisition module is activated and supplementary lighting is turned on. For example, before and during the spin-drying process, images of the door seal area are continuously acquired at a certain frame rate (e.g., 10fps).

[0107] The image acquisition module can utilize a wide-angle waterproof camera, such as a 2-megapixel waterproof camera with a 120° wide-angle field of view. To obtain the optimal monitoring angle and balance installation and protection requirements, such as... Figure 2 As shown, the camera can be selectively embedded in the door glass 6 (the camera is not shown here) or built into the lifting rib 4. Preferably, when the image acquisition module 1 is placed inside the lifting rib 4, a retractable structure can be adopted. To cope with the dim lighting environment inside the tube, the clothing handling device is also equipped with a supplementary lighting module (such as an LED downlight). This module can be triggered synchronously with the camera to provide uniform illumination during image acquisition, ensuring image quality.

[0108] Optionally, image processing can be performed by an edge computing module, such as using the Rockchip RK3588 chip. This module is directly deployed within the washing machine controller and is responsible for running the image recognition algorithm. Its processing latency can be controlled within 150 milliseconds, meeting real-time requirements. To reduce overall power consumption, an event-triggered wake-up mechanism is also adopted: during non-spinning stages or when there is no significant risk, the image acquisition module and processing module are in a low-power standby state, with power consumption below 0.5W; when entering the spin-drying stage or other preset trigger conditions (such as after the door is closed or before high-speed rotation) are met, they are woken up and enter full-function working mode, acquiring image data collected by the image acquisition module through the edge computing module's interface, and then performing image processing, etc.

[0109] In order to control the camera, such as Figure 2 As shown, the lifting rib 4 is also equipped with a telescopic drive mechanism 5, which includes a drive source and a transmission mechanism. Optionally, a miniature, high-torque stepper motor or a miniature linear motor is selected as the power source, and a cam-linkage combination mechanism is used to achieve precise linear telescopic motion. The rotating output shaft of the motor is connected to a cam with a specific profile. The profile surface of the cam contacts one end of a driven link, and the other end of the link is rigidly connected to the camera support platform through a slide rail. When the motor rotates to the first angle, it pushes the link to put the camera in the fully retracted storage position; when the motor rotates to the second angle, it smoothly pushes the camera out to the working position.

[0110] After the camera retracts into its original position, the main control unit releases the forced constraint on the position of the lifting ribs, allowing the washing drum to rotate freely to any desired position as needed for the washing or spin-drying process.

[0111] To achieve a progressive solution ranging from gentle rinsing to mechanical intervention, based on the complexity of the clothing jamming, some embodiments also include a clamping device fitted to the lifting rib.

[0112] Once mechanical intervention is initiated, the washing drum is first rotated to move the gripping device to the vicinity of the garment inside the drum that is connected to the foreign object. Then, the grippers extend to stably hold the target garment. While the grippers apply a stable pulling force, the washing drum is simultaneously rotated at a low speed or oscillated at a small angle (e.g., rotating 10-20 degrees per second in a direction conducive to release). This coordinated pulling and tugging effectively amplifies the release force and avoids damage to the garment caused by pulling in one direction.

[0113] In addition, the dragging action can be designed as an oscillating motion, that is, the grippers perform high-frequency micro-amplitude reciprocating motion while maintaining the clamping force, so as to more gently break the fiber entanglement.

[0114] Optionally, the clamping device integrates a pressure sensor to monitor the clamping force in real time. When the pulling force exceeds a preset safety threshold for clothing, the dragging stops immediately to prevent damage to the clothing.

[0115] This embodiment can automatically select and execute a progressive solution, from gentle rinsing to mechanical intervention, based on the complexity of the clothing jamming.

[0116] It should be noted that when the camera and clamping device are installed inside the lifting rib, the image needs to be transmitted to the processor via in-drum power supply technology, waterproof cable, or wireless module. This embodiment does not limit the specific implementation method of in-drum power supply; all solutions that can achieve in-drum power supply are applicable to this application. For example, the invention described in patent application CN202211607494.0, entitled "A Device for Powering the Inside of a Drum Washing Machine and a Washing Machine," and patent application CN2023116816837, also entitled "A Device for Powering the Inside of a Drum Washing Machine and a Washing Machine," etc.

[0117] This embodiment does not limit the specific implementation of the clamping device; all solutions integrated into the lifting ribs that can clamp clothes are included in this application. For example, Chinese Patent ZL202223339070.9 discloses a washing machine clothes clamping device based on light judgment results; and the clamping device described in the patent application with application number CN202410236754.0, entitled "A Washing Control Method and Washing Device That Can Automatically Hang Clothes".

[0118] The clothing processing device of this embodiment may include the following process: The image acquisition module is used to acquire the image of the door sealing area; The image processing module is used to process and analyze the image of the door seal area to identify whether there is clothing stuck in the gap of the door seal. The unclamping module is used to unclamp clothing when it detects that clothing is clamped.

[0119] Based on the technical solution of the above embodiments, optionally, the step of processing and analyzing the image of the door sealing area includes: The image of the door seal area is subjected to HSV color space conversion and adaptive threshold segmentation to enhance the edge contrast between the door seal and the clothing. Analyze motion features in image sequences based on optical flow methods, and / or identify the contours of foreign objects in images based on object detection models.

[0120] Based on the technical solutions of the above embodiments, optionally, the target detection model is a YOLO model trained on a dataset, the dataset containing sample images of various lighting conditions and clothing materials synthesized through a generative adversarial network.

[0121] Based on the technical solution of the above embodiments, optionally, the operation of untying the clothing includes a water-fluid agitation untying step: The water inlet system of the garment processing device is controlled to perform spraying to raise the water level in the washing drum of the garment processing device; Adjust the motor drive mode of the clothing handling device so that the washing drum swings forward and backward at a preset low speed. The water flow generated by the low-speed oscillation impacts and carries away clothing caught in the gaps of the door seal.

[0122] Based on the technical solution of the above embodiments, optionally, the water flow turbulence unclamping step further includes: After the preset unclamping attempt time has elapsed, the door seal area image is captured again to determine whether the clothing has been successfully unclamped. If it is confirmed that the clothes have been untangled, control the drainage to lower the water level and resume the washing program at the original normal cycle.

[0123] Based on the technical solution of the above embodiments, optionally, when clothing is detected to be clipped, the method further includes the following step: Analyze the morphological characteristics of the foreign object stuck in the tub; wherein, the morphological characteristics of the foreign object include at least one of the stuck area of ​​the foreign object, the type of foreign object, and the connection relationship between the foreign object and the clothes inside the tub, and the type of foreign object includes independent small items, clothing parts, and long strips of fabric; Based on the jamming morphology characteristics, a corresponding unjamming operation is selected and executed from at least two preset unjamming strategies, wherein the water flow turbulence unjamming step is configured as a basic unjamming operation in the at least two unjamming strategies.

[0124] Based on the technical solution of the above embodiments, optionally, the lifting rib of the garment handling device is equipped with a clamping device, and the step of selecting and executing the corresponding unclamping operation from at least two preset unclamping strategies includes: When the condition is determined to be a first type of stuck state, the water flow turbulence release step is executed; When the condition is determined to be a second type of jamming, a two-stage unclamping strategy is executed: the washing drum is controlled to rotate so that the clamping device moves to the vicinity of the clothing body connected to the foreign object, and then the clamping device is controlled to clamp the clothing inside the drum connected to the foreign object and perform a dragging action to pull the foreign object into the drum.

[0125] Based on the technical solutions of the above embodiments, optionally, the first type of jamming state is defined as: the jamming area of ​​the foreign object is less than a threshold, the type of foreign object is an independent small part and the connection relationship is independent; The second type of stuck state is defined as: the foreign object is a piece of clothing or a long strip of fabric, and / or the foreign object is connected to the clothing inside the tube.

[0126] Based on the technical solutions of the above embodiments, optionally, the dragging action of the clamping device is coordinated with the auxiliary low-speed rotation or oscillation of the washing drum.

[0127] Based on the technical solution of the above embodiments, optionally, during or after the execution of the corresponding unclamping operation step selected from at least two preset unclamping strategies, the door seal area image is continuously or re-acquired to determine whether the unclamping is successful; if successful, the normal washing program is restored; if unsuccessful, the final security strategy, including shutdown and user alarm, is triggered.

[0128] Based on the technical solutions of the above embodiments, optionally, the image acquisition module is a retractable camera disposed inside the lifting rib of the clothing processing device; and further includes the following before the step of acquiring the image of the door sealing area: The washing drum of the garment processing device is rotated to move the lifting rib to the preset shooting area; Control the camera to extend the lifting rib to the working position to acquire images; After the data acquisition is completed, the camera is retracted into its storage position inside the lifting rib.

[0129] This embodiment provides a garment handling device that achieves intelligent sensing and proactive intervention in anti-clogging conditions, fundamentally improving user experience and safety. Within the operating cycle of the garment handling device, a closed-loop intelligent solution path is constructed for garments caught in the door seal. Through image acquisition and intelligent analysis, it can automatically and in real time identify garment-catching conditions that are easily overlooked by humans or undetectable by traditional sensors, and immediately trigger the corresponding unclogging procedure. This completely changes the passive situation where users need to handle faults afterward, avoiding program interruptions, garment damage, and even safety hazards caused by garment catching, providing a worry-free, intervention-free washing experience.

[0130] This embodiment overcomes the technical limitations of traditional mechanical error prevention and simple sensing, significantly improving the accuracy and reliability of detection. Compared to passive protection measures such as optimizing the shape of the door seal, this embodiment adopts a vision-based active perception scheme, which can adapt to different clothing materials, shapes, and jamming angles, making it highly versatile. Compared to simple contact or photoelectric sensors, the image recognition method in this embodiment can not only determine whether there is a foreign object, but also further analyze what the object is and its jamming morphological characteristics (such as jamming area, type, and whether it is connected to the clothing inside the garment). This multi-dimensional state recognition provides a reliable basis for subsequent execution of differentiated and precise unblocking strategies, greatly reducing false alarms and false negatives.

[0131] This embodiment proposes a tiered and collaborative intelligent unclamping strategy, achieving efficient and flexible fault handling. Instead of simply triggering an alarm or shutting down the machine, this embodiment executes a tiered response strategy, ranging from hydraulic agitation to mechanical intervention, based on intelligent analysis of the jamming morphology. For example, for loose, small foreign objects, non-contact water jet flushing is prioritized to unclamp them, maximizing the protection of clothing; for tightly packed or connected jams, active intervention such as mechanical clamping is initiated. This collaborative handling mechanism, employing a combination of gentle and forceful approaches, efficiently resolves the problem while ensuring the protection of clothing and the machine itself, demonstrating a high degree of intelligence and human-centered design.

[0132] This embodiment extends the service life of the core components of the equipment and improves the overall reliability of the product. Abnormal friction and impact between the door seal and the inner drum are the main causes of premature aging and damage. This embodiment effectively prevents continuous impact and wear on the door seal during high-speed spin-drying by timely detection and release of jams, and also avoids the risk of damage to the inner drum bearings due to long-term abnormal stress. This fundamentally reduces maintenance needs caused by such failures and lowers the total life cycle cost of the product.

[0133] Example 3 A computer device 400, such as Figure 9As shown, the device includes a memory 410, a processor 420, and a computer program 430 stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a control method for a garment handling device. For a detailed description of the method, please refer to the corresponding description in the above method embodiments; it will not be repeated here.

[0134] Example 4 A computer-readable storage medium, such as Figure 10 As shown, a computer program is stored thereon, which, when executed by a processor, implements the steps of a control method for a garment handling device. For a detailed description of the method, please refer to the corresponding description in the above method embodiments, and will not be repeated here.

[0135] The number of devices and processing scale described herein are for the purpose of simplifying the description of the invention. Applications, modifications, and variations of the invention will be readily apparent to those skilled in the art.

[0136] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

[0137] The apparatus, computer device, and non-volatile computer storage medium and method provided in the embodiments of this specification are corresponding. Therefore, the apparatus, computer device, and non-volatile computer storage medium also have similar beneficial technical effects as the corresponding method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the corresponding apparatus, computer device, and non-volatile computer storage medium will not be repeated here.

[0138] Those skilled in the art will also know that, besides implementing the controller in the form of purely computer-readable program code, the same functions can be achieved by logically programming the method steps, making the controller take the form of logic gates, switches, application-specific integrated circuits (ASICs), programmable logic controllers (PLCs), and embedded microcontrollers. Therefore, such a controller can be considered a hardware component, and the devices included within it for implementing various functions can also be considered structures within that hardware component. Alternatively, the devices for implementing various functions can be considered as both software units implementing the method and structures within a hardware component.

[0139] The systems, apparatuses, or units described in the above embodiments can be implemented by computer chips or physical entities, or by products with certain functions. For ease of description, the above apparatuses are described separately as various units based on their functions. Of course, when implementing one or more embodiments of this specification, the functions of each unit can be implemented in one or more software and / or hardware.

[0140] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0141] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0142] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0143] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0144] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0145] This specification may be described in the general context of computer-executable instructions, such as program units, that are executed by a computer. Generally, program units include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification may also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program units may reside in local and remote computer storage media, including storage devices.

[0146] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0147] The above description is merely an embodiment of this specification and is not intended to limit the scope of one or more embodiments of this specification. Various modifications and variations can be made to one or more embodiments of this specification by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principle of one or more embodiments of this specification should be included within the scope of the claims of one or more embodiments of this specification.

Claims

1. A control method for a garment handling device, characterized in that, The garment processing device is equipped with an image acquisition module, which is used to acquire images of the door sealing area of ​​the garment processing device, including the following steps: Obtain the image of the door sealing area; The image of the door seal area is processed and analyzed to identify whether there is clothing stuck in the gap of the door seal; When clothing is detected to be stuck inside, the clothing is unstuck.

2. The control method for a garment handling device as described in claim 1, characterized in that, The steps for processing and analyzing the image of the door sealing area include: The image of the door seal area is subjected to HSV color space conversion and adaptive threshold segmentation to enhance the edge contrast between the door seal and the clothing. Analyze motion features in image sequences based on optical flow methods, and / or identify the contours of foreign objects in images based on object detection models.

3. The control method for a garment processing device as described in claim 2, characterized in that, The object detection model is a YOLO model trained on a dataset containing sample images of various lighting conditions and clothing materials synthesized through a generative adversarial network.

4. The control method for a garment processing device as described in claim 2, characterized in that, The operation of untangling the clothing includes the step of using water agitation to untangle it: The water inlet system of the garment processing device is controlled to perform spraying to raise the water level in the washing drum of the garment processing device; Adjust the motor drive mode of the clothing handling device so that the washing drum swings forward and backward at a preset low speed. The water flow generated by the low-speed oscillation impacts and carries away clothing caught in the gaps of the door seal.

5. The control method for a garment handling device as described in claim 4, characterized in that, The water flow agitation and unclamping step also includes: After the preset unclamping attempt time has elapsed, the door seal area image is captured again to determine whether the clothing has been successfully unclamped. If it is confirmed that the clothes have been untangled, control the drainage to lower the water level and resume the washing program at the original normal cycle.

6. The control method for a garment handling device as described in claim 4, characterized in that, When clothing is detected, the process also includes the following steps: Analyze the morphological characteristics of the foreign object stuck in the tub; wherein, the morphological characteristics of the foreign object include at least one of the stuck area of ​​the foreign object, the type of foreign object, and the connection relationship between the foreign object and the clothes inside the tub, and the type of foreign object includes independent small items, clothing parts, and long strips of fabric; Based on the jamming morphology characteristics, a corresponding unjamming operation is selected and executed from at least two preset unjamming strategies, wherein the water flow turbulence unjamming step is configured as a basic unjamming operation in the at least two unjamming strategies.

7. The control method for a garment handling device as described in claim 6, characterized in that, The lifting ribs of the garment handling device are equipped with a clamping device, and the step of selecting and executing the corresponding unclamping operation from at least two preset unclamping strategies includes: When the condition is determined to be a first type of stuck state, the water flow turbulence release step is executed; When the condition is determined to be a second type of jamming, a two-stage unclamping strategy is executed: the washing drum is controlled to rotate so that the clamping device moves to the vicinity of the clothing body connected to the foreign object, and then the clamping device is controlled to clamp the clothing inside the drum connected to the foreign object and perform a dragging action to pull the foreign object into the drum.

8. The control method for a garment handling device as described in claim 7, characterized in that, The first type of jamming state is defined as follows: the jamming area of ​​the foreign object is less than a threshold, the foreign object type is an independent small piece and the connection relationship is independent; The second type of stuck state is defined as: the foreign object is a piece of clothing or a long strip of fabric, and / or the foreign object is connected to the clothing inside the tube.

9. The control method of the garment handling device as described in claim 7, characterized in that, The pulling action of the clamping device is coordinated with the auxiliary low-speed rotation or oscillation of the washing drum.

10. The control method of the garment handling device as described in claim 6, characterized in that, During or after the execution of the corresponding unclamping operation step selected from at least two preset unclamping strategies, images of the door seal area are continuously or re-acquired to determine whether the unclamping is successful. If successful, the normal washing program is resumed; if unsuccessful, the final security strategy, including shutdown and user alarm, is triggered.

11. The control method of the garment handling device as described in claim 1, characterized in that, The image acquisition module is a retractable camera installed inside the lifting rib of the clothing processing device; prior to the step of acquiring the image of the door sealing area, the following is also included: The washing drum of the garment processing device is rotated to move the lifting rib to the preset shooting area; Control the camera to extend from inside the lifting rib to acquire images; After the data acquisition is completed, the camera is retracted into the lifting rib.

12. A garment processing device, characterized in that, include: An image acquisition module, which is mounted on the door glass or lifting rib of the clothing processing device, is used to acquire images of the door sealing area; The main control unit is configured to perform the method as described in any one of claims 1 to 11.

13. The garment processing apparatus as described in claim 12, characterized in that, It also includes a clamping device, which is assembled to the lifting rib.

14. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 11.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 11.

Images