Rapier weft insertion adjusting method and device based on loom opening yarn detection

Abstract

The invention discloses a rapier weft insertion adjusting method and device based on loom opening yarn detection, and belongs to the field of intelligent control of textile machinery. The method comprises the following steps: acquiring image data for representing an opening form of a loom and an optical fiber signal for representing a yarn state in an opening area of the loom; performing anomaly detection on the image data and the optical fiber signal with the same timestamp according to a preset detection algorithm to obtain a detection result; according to the detection result, whether opening abnormity exists in the loom or not is determined, if yes, a rapier obstacle avoidance path is generated according to a preset rapier obstacle avoidance algorithm to adjust the rapier movement track, and if not, normal weaving is conducted according to the preset process. According to the invention, the opening detection precision of fabrics with complex structures can be improved, and the weaving efficiency is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology for textile machinery, and in particular to a method and device for adjusting the weft insertion of the rapier based on the detection of the sheath yarn on the loom. Background Technology

[0002] Three-dimensional woven preforms, with their lightweight, high strength, and excellent mechanical properties, are widely used in aerospace, defense, and other fields as key reinforcing structures for high-performance composite materials. However, during the preform weaving process, tension fluctuations in the warp system can easily lead to unclear shedding, yarn slack, insufficient shedding height, and yarn suspension. If the rapier weft insertion mechanism fails to respond in time, process failures such as yarn collision and snagging can easily occur, seriously affecting the weaving quality and production efficiency of the preforms.

[0003] In related technologies, vision systems are typically used for opening morphology detection. These systems acquire opening images and compare them with a preset template, outputting a stop signal when a deviation is detected. However, this method has low accuracy when detecting openings in complex fabric structures, and manual adjustments are still required when anomalies occur, resulting in a significant reduction in the weaving efficiency of the loom.

[0004] Therefore, there is an urgent need for a rapier weft insertion adjustment method and device based on the detection of sheathed yarn on a loom to solve the above-mentioned technical problems. Summary of the Invention

[0005] This invention provides a rapier weft insertion adjustment method and device based on the detection of shedding yarn on a loom, which can improve the accuracy of shedding detection for complex fabrics and increase weaving efficiency. The technical solution is as follows: On the one hand, a method for adjusting the weft insertion of the rapier based on the detection of the sheath yarn on a loom is provided, the method comprising: Acquire image data to characterize the shedding morphology of the loom and optical fiber signals to characterize the yarn state in the shedding area of ​​the loom; Anomaly detection is performed on image data and fiber optic signals with the same timestamp according to the preset detection algorithm, and the detection results are obtained. Based on the test results, determine whether there is an abnormal sheathing in the loom. If so, generate a rapier obstacle avoidance path according to the preset rapier obstacle avoidance algorithm to adjust the rapier movement trajectory; otherwise, proceed with the weaving normally according to the preset process.

[0006] On the other hand, a rapier weft insertion adjustment device based on the detection of sheathed yarn on a loom is provided, the device comprising: The acquisition module is used to acquire image data that characterizes the sheath shape of the loom and optical fiber signals that characterize the yarn state in the sheath area of ​​the loom. The detection module is used to perform anomaly detection on image data and fiber optic signals with the same timestamp according to a preset detection algorithm, and obtain the detection results. The obstacle avoidance module is used to determine whether there is an abnormal sheathing of the loom based on the detection results. If so, it generates a rapier obstacle avoidance path according to the preset rapier obstacle avoidance algorithm to adjust the rapier movement trajectory; otherwise, it carries out weaving normally according to the preset process.

[0007] On the other hand, a computer device is provided, the computer device including a memory and a processor, the memory for storing computer programs, and the processor for executing the computer programs stored in the memory to implement the steps of the rapier weft insertion adjustment method based on the detection of open yarn on a loom as described above.

[0008] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when the computer program is executed by a processor, the steps of the rapier weft insertion adjustment method based on the detection of sheath yarn on a loom are implemented as described above.

[0009] On the other hand, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the rapier weft insertion adjustment method based on the detection of sheath yarn on a loom as described above.

[0010] The technical solution provided by this invention can bring at least the following beneficial effects: First, it uses an image acquisition device to capture high-definition image data of the opening area in real time, and simultaneously acquires optical fiber signals to characterize the abnormal state of the yarn in the opening area of ​​the loom; then, it analyzes and processes the image data through a preset detection algorithm to determine whether there is an anomaly, and performs time-synchronized fusion with the optical fiber sensing signal, and determines a fault when any anomaly is triggered; finally, it generates a path point sequence based on an obstacle avoidance algorithm, and precisely adjusts the tracking trajectory of the rapier servo motor to ensure the normal operation of the loom. This method improves the recognition accuracy of yarn opening anomalies through dual detection of optics and optical fibers, effectively solves the yarn anomaly problem in high-speed weaving, and significantly improves the weaving efficiency and quality stability of carbon fiber preforms. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a rapier weft insertion adjustment method based on loom sheath yarn detection provided in an embodiment of the present invention; Figure 2This is a flowchart of the operation of a rapier weft insertion adjustment system based on the detection of sheathed yarn on a loom, according to an embodiment of the present invention. Figure 3 This is a front view of a rapier weft insertion adjustment device provided in an embodiment of the present invention; Figure 4 This is an axial view of a rapier weft insertion adjustment device provided in an embodiment of the present invention; Figure 5 This is an example image captured by an image acquisition camera according to an embodiment of the present invention; Figure 6 This is a schematic diagram of an optical fiber sensor provided in an embodiment of the present invention; Figure 7 This is an example diagram illustrating yarn obstruction during the opening process according to an embodiment of the present invention; Figure 8 This is a schematic diagram of a pneumatic nozzle structure provided in an embodiment of the present invention; Figure 9 This is a schematic diagram of the ROI region provided in an embodiment of the present invention; Figure 10 This is a schematic diagram of a binarized image obtained through processing according to an embodiment of the present invention; Figure 11 This is a structural diagram of a rapier weft insertion adjustment device based on the detection of open yarn on a loom, according to an embodiment of the present invention. Figure 12 This is a hardware architecture diagram of a computer device provided in an embodiment of the present invention.

[0013] Figure descriptions: 1-Rapier support; 2-Camera support; 3-Camera; 4-Rapier; 5-Rapier drive motor; 6-Fiber optic sensor transmitter; 7-Fiber optic sensor receiver; 8-LED light source; 9-Pneumatic nozzle; 10-Rapier moving device; 11-Weft selection moving device. Detailed Implementation

[0014] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0015] As mentioned earlier, existing methods have low accuracy when detecting openings in complex fabrics, and manual adjustments are still required when anomalies occur, which greatly reduces the working efficiency of the loom.

[0016] Based on this, the concept of the present invention is to improve the accuracy of identifying abnormal loom openings by using both image and fiber optic detection methods, and to generate obstacle avoidance paths through a preset rapier obstacle avoidance algorithm to ensure the normal operation of the loom.

[0017] The following describes the specific implementation of the above concept.

[0018] Please refer to Figure 1 The present invention provides a rapier weft insertion adjustment method based on the detection of sheathed yarn on a loom, the method comprising: Step 100: Acquire image data to characterize the loom opening morphology and optical fiber signals to characterize the yarn state in the loom opening area; Step 102: Perform anomaly detection on image data and fiber optic signals with the same timestamp according to the preset detection algorithm to obtain the detection results; Step 104: Determine whether there is an abnormal sheathing of the loom based on the detection results. If so, generate a rapier obstacle avoidance path according to the preset rapier obstacle avoidance algorithm to adjust the rapier movement trajectory; otherwise, weaving proceeds normally according to the preset process.

[0019] In this embodiment of the invention, firstly, a high-definition image data of the yarn sheathing area is captured in real time using an image acquisition device, while simultaneously acquiring fiber optic signals to characterize abnormal yarn conditions in the sheathing area of ​​the loom. Next, a preset detection algorithm is used to analyze and process the image data to determine if any abnormality exists, and this data is fused with the fiber optic sensor signal in time synchronization. Any abnormality triggering results in a fault determination. Finally, a path point sequence is generated based on an obstacle avoidance algorithm, and the tracking trajectory of the rapier servo motor is precisely adjusted to ensure the normal operation of the loom. This method improves the accuracy of yarn sheathing abnormality identification through dual optical and fiber optic detection, effectively solving the yarn abnormality problem in high-speed weaving and significantly improving the weaving efficiency and quality stability of carbon fiber preforms.

[0020] The following is combined with Figure 1 and Figure 2 The description shows how each step is performed.

[0021] First, for step 100, image data for characterizing the loom opening morphology and optical fiber signals for characterizing the yarn state in the loom opening area are acquired.

[0022] like Figure 3 and Figure 4 As shown, in this embodiment of the invention, image data is acquired through a preset image sensor. This sensor includes two industrial-grade high-definition cameras (2 megapixels or higher) and a strip LED light source. The two cameras are mounted side-by-side on the outside of the rapier guide rail using an aluminum alloy bracket, and rise and fall synchronously with the rapier for real-time image acquisition. Figure 5 The image shows the opening region.

[0023] Specifically, two high-definition industrial cameras are equipped with 16mm fixed-focus lenses. The cameras are fixedly mounted to the outside of the rapier guide rail using aluminum alloy brackets, allowing for synchronized vertical movement with the rapier. A strip-shaped LED light source is mounted on the weft selection system frame, secured with a dedicated bracket, and can rise and fall synchronously with the weft selection system. The light source is powered by a constant current driver, providing uniform backlighting in the opening area.

[0024] The fiber optic signal is acquired through a pre-set fiber optic sensor. A regional fiber optic sensor, consisting of a transmitting fiber bundle and a receiving fiber bundle, is used to cover the opening area with a light strip, such as... Figure 6 As shown, it identifies abnormal conditions such as loose yarn and drooping yarn. The built-in amplification and filtering circuit converts the optical intensity signal at the fiber optic receiver into a digital level.

[0025] For example, an FT-a32 area fiber optic sensor can be used, with the transmitter and receiver mounted on dedicated brackets on the rapier side and weft selection side, respectively. The probe spacing is adjusted to 150mm, forming a light curtain covering the entire width of the loom. The sensor sensitivity is set to trigger upon detecting yarn obstruction with a diameter of 0.5mm or larger, and the digital signal is transmitted in real time via a bus to subsequent detection and obstacle avoidance modules, for example... Figure 7 The diagram shows the situation where the open yarn is covered.

[0026] It is worth noting that, considering the possibility of yarn curling upwards at the edge of the loom during the weaving process, this embodiment also includes a method to blow the curled yarns down. Figure 8 The pneumatic nozzle shown is a 3D-printed flat nozzle made of ABS resin. The nozzle outlet has a narrow, flat structure with a length of 20mm and a width of 1.5mm, and an airflow diffusion angle >60 degrees. The nozzle is connected to the pneumatic system via a solenoid valve, and the working air pressure is stabilized at 0.4-0.6MPa. The nozzle is mounted above the area fiber optic sensor and continuously sprays air downwards to disperse minor yarn obstructions.

[0027] Then, for step 102, anomaly detection is performed on image data and fiber optic signals with the same timestamp according to the preset detection algorithm to obtain the detection results.

[0028] In this embodiment of the invention, the core processor for detecting image data and fiber optic signals is an Advantech UNO-2484G industrial-grade embedded industrial control computer equipped with an Intel i7 processor. After the industrial control computer starts up, it automatically loads preset system parameters, including image acquisition parameters, motion control parameters, and various detection thresholds, and completes the self-test and readiness status confirmation of each hardware module.

[0029] Furthermore, a hardware triggering mechanism is used to achieve synchronous acquisition of multi-source data. The motion control card sends a synchronization signal the instant the rapier begins to move, simultaneously triggering dual-camera image acquisition and fiber optic sensor data acquisition, and assigning a unified timestamp to all data to ensure the time consistency of data processing.

[0030] In this embodiment of the invention, anomaly detection of image data and fiber optic signals with the same timestamp includes: detecting the intelligently processed image data and determining that images meeting preset characteristics in the detection results are abnormal images; filtering the fiber optic signals and determining that signals with light intensity attenuation greater than a preset threshold after filtering are abnormal signals.

[0031] Specifically, this embodiment uses a core algorithm that combines intelligent localization of yarn anomaly search areas with anomaly detection based on Blob analysis to analyze image data: First, an edge feature matching algorithm is used to locate the upper and lower boundaries of the opening. Then, a dynamic ROI generation technique is used to automatically generate a dynamic rectangular detection region between the upper and lower boundary lines, such as... Figure 9 As shown, this region adaptively adjusts as the opening shape changes.

[0032] Next, the image data within the rectangular detection area is filtered and denoised, and then converted into a binary image using adaptive threshold segmentation, such as... Figure 10 As shown, this is to separate the abnormal yarn from the background.

[0033] For example, Gaussian filtering is applied to the image within the region to remove noise, and then the cv2.adaptiveThreshold() function in the OpenCV library is used for adaptive thresholding to obtain a high-contrast binary image, where the abnormal yarn is white (255) and the background is black (0).

[0034] Furthermore, connected component analysis is performed on the binary image according to a preset function, and the geometric and morphological features of interconnected pixel regions in each binary image are calculated based on the analysis results; all calculation results are identified according to preset abnormal features, and images that meet the abnormal features are determined to be abnormal images.

[0035] For example, the `cv2.connectedComponentsWithStats()` function performs connected component analysis on binary images, calculating the geometric and morphological features of interconnected pixel regions (blobs) in each binary image. For instance, if a blob has an area > 50 pixels and an aspect ratio > 4, it is classified as "slack yarn". Once a blob matching these features is found, the pixel region is immediately identified as an anomaly.

[0036] Furthermore, for fiber optic signals, when the fiber optic sensor detects fiber optic obstruction, that is, when the light intensity attenuation after filtering is greater than a preset threshold, such as 15%, it is determined to be "fiber optic detection abnormal," and this signal is an abnormal signal.

[0037] For step 104, determine whether there is an abnormal sheathing of the loom based on the detection results. If so, generate a rapier obstacle avoidance path according to the preset rapier obstacle avoidance algorithm to adjust the rapier movement trajectory; otherwise, weaving proceeds normally according to the preset process.

[0038] In this embodiment of the invention, it is determined whether there is an abnormal image or an abnormal signal at the same timestamp. If so, it is determined that the loom has an opening abnormality; otherwise, it is determined that the loom does not have an opening abnormality. That is to say, as long as either of the two is triggered simultaneously, an opening fault is determined, and subsequent obstacle avoidance intervention procedures are initiated.

[0039] In this embodiment of the invention, generating a sword pole obstacle avoidance path according to a preset sword pole obstacle avoidance algorithm to adjust the sword pole's motion trajectory includes the following steps: First, the rectangular detection area of ​​the abnormal image is mapped to a preset spatial coordinate system, and the mapped area is marked as the obstacle area; wherein, the spatial coordinate system is obtained by discretizing the motion plane of the sword; the size of the obstacle will be increased by 2mm on the basis of the actual circumscribed rectangle to ensure that the sword can pass safely even if there are small tracking errors.

[0040] Next, the current position of the rapier is taken as the starting point of the path, and the safe endpoint of the latitude guide is taken as the target point of the path. The A-StarAlgorithm is then input to obtain the sequence of collision-free shortest path points from the starting point to the target point in the obstacle region: .

[0041] Finally, curve fitting is performed on the collision-free shortest path point sequence based on spline curves to obtain a smooth path for tracking the rapier motion mechanism.

[0042] Furthermore, the difference between the real-time position of the sword stick and the smooth path is determined by the PID controller, and a control quantity is output to the servo driver according to the difference to adjust the movement of the sword stick along the smooth path.

[0043] Specifically, the purpose of the PID controller is to enable the actual position of the sword stick to quickly, accurately, and smoothly track the planned desired position. By reading the feedback value of the servo motor encoder, the real-time position r(t) of the sword stick is obtained. This position is compared with the desired path point T(t) to obtain the position tolerance e(t). Using the classic PID control algorithm, a control quantity u(t) is output as an analog voltage to the driver of the servo motor that drives the sword stick. The driver adjusts the motor speed and torque according to the command, ultimately driving the sword stick to move, eliminating position deviation, and thus achieving precise control of its motion trajectory.

[0044] It is worth noting that after generating a scimitar obstacle avoidance path according to the preset scimitar obstacle avoidance algorithm to adjust the scimitar movement trajectory, the method further includes: when the scimitar obstacle avoidance algorithm cannot generate a scimitar obstacle avoidance path, it is determined that the scimitar cannot pass through the opening by moving its position. At this time, the scimitar is stopped and an alarm is triggered to wait for manual handling.

[0045] In summary, this method achieves intelligent sensing and precise control of the loom's sheathing state, effectively solving the problem of yarn collision in high-performance weaving. Each parameter can be adjusted according to actual production needs, demonstrating good adaptability and scalability.

[0046] Please refer to Figure 11 This invention provides a rapier weft insertion adjustment device based on the detection of sheathed yarn on a loom. The device includes: The acquisition module M1 is used to acquire image data that characterizes the sheath shape of the loom and optical fiber signals that characterize the yarn state in the sheath area of ​​the loom. The detection module M2 is used to perform anomaly detection on image data and fiber optic signals with the same timestamp according to a preset detection algorithm, and obtain the detection results. The obstacle avoidance module M3 is used to determine whether there is an abnormal sheathing of the loom based on the detection results. If so, it generates a rapier obstacle avoidance path according to the preset rapier obstacle avoidance algorithm to adjust the rapier movement trajectory; otherwise, it carries out weaving normally according to the preset process.

[0047] In this embodiment of the invention, when the detection module M2 performs anomaly detection on image data and fiber optic signals with the same timestamp according to a preset detection algorithm and obtains the detection results, it specifically performs the following operations: detects the intelligently processed image data and determines that the images in the detection results that meet the preset characteristics are abnormal images; filters the fiber optic signals and determines that the signals whose light intensity attenuation after filtering is greater than a preset threshold are abnormal signals.

[0048] In this embodiment of the invention, when the detection module M2 performs detection on the intelligently processed image data and determines that an image satisfying preset features in the detection results is an abnormal image, it specifically performs the following operations: locates the upper and lower boundaries of the opening according to an edge feature matching algorithm, generating an adaptive rectangular detection region that changes with the shape of the opening; performs filtering and noise reduction processing on the image data within the rectangular detection region, and converts the processed data into a binary image through adaptive threshold segmentation to separate the abnormal yarn from the background; performs connected component analysis on the binary image according to a preset function, and calculates the geometric and morphological features of interconnected pixel regions in each binary image based on the analysis results; identifies all calculation results according to preset abnormal features, and determines that an image conforming to the abnormal features is an abnormal image.

[0049] In this embodiment of the invention, when the obstacle avoidance module M3 determines whether the loom has an opening abnormality based on the detection results, it specifically performs the following operations: it determines whether there is an abnormal image or abnormal signal at the same timestamp; if so, it determines that the loom has an opening abnormality; otherwise, it determines that the loom does not have an opening abnormality.

[0050] In this embodiment of the invention, when the obstacle avoidance module M3 generates an obstacle avoidance path for the sparring pole according to a preset obstacle avoidance algorithm to adjust the sparring pole's motion trajectory, it specifically performs the following operations: mapping the rectangular detection area of ​​the abnormal image to a preset spatial coordinate system, and marking the mapped area as an obstacle area; wherein, the spatial coordinate system is obtained by discretizing the motion plane of the sparring pole; taking the current position of the sparring pole as the path starting point and the safe latitude endpoint as the path target point, inputting the A-Star Algorithm algorithm, and outputting the sequence of collision-free shortest path points from the path starting point to the path target point in the obstacle area; performing curve fitting on the sequence of collision-free shortest path points according to a spline curve to obtain a smooth path for tracking the sparring pole's motion mechanism; determining the difference between the real-time position of the sparring pole and the smooth path through a PID controller, and outputting a control quantity to the servo driver according to the difference to adjust the sparring pole's movement along the smooth path.

[0051] In this embodiment of the invention, after generating a sword pole obstacle avoidance path according to a preset sword pole obstacle avoidance algorithm to adjust the sword pole movement trajectory, the method further includes: when the sword pole obstacle avoidance algorithm cannot generate a sword pole obstacle avoidance path, determining that the sword pole cannot pass through the opening by moving its position, stopping the sword pole movement and triggering an alarm to await manual handling.

[0052] It should be noted that the rapier weft insertion adjustment device based on loom shedding yarn detection provided in the above embodiments is only an example illustrating the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. Furthermore, the rapier weft insertion adjustment device based on loom shedding yarn detection provided in the above embodiments and the rapier weft insertion adjustment method embodiment based on loom shedding yarn detection belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0053] Embodiments of this application also provide a computer device, please refer to... Figure 12 The computer device includes a processor and a memory, the memory storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, at least one program, code set or instruction set being loaded and executed by the processor to implement the rapier weft insertion adjustment method based on loom sheath yarn detection provided in the above method embodiments.

[0054] Embodiments of this application also provide a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, at least one program, code set, or instruction set is loaded and executed by a processor to implement the rapier weft insertion adjustment method based on loom sheath yarn detection provided in the above-described method embodiments.

[0055] Embodiments of this application also provide a computer program product, which includes a computer program. A processor of a computer device reads the computer program from a computer-readable storage medium and executes the computer program, causing the computer device to perform the rapier weft insertion adjustment method based on loom sheath yarn detection as described in any of the above embodiments.

[0056] For ease of description, the above systems or devices are described separately as various modules or units based on their functions. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware components.

[0057] As can be seen from the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of this application.

[0058] Finally, it should be noted that in this document, relational terms such as first, second, third, and fourth are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, 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 limitations, 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.

[0059] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for adjusting rapier weft insertion based on the detection of sheathed yarn on a loom, characterized in that, The method includes: Acquire image data to characterize the shedding morphology of the loom and optical fiber signals to characterize the yarn state in the shedding area of ​​the loom; Anomaly detection is performed on image data and fiber optic signals with the same timestamp according to the preset detection algorithm, and the detection results are obtained. Based on the test results, determine whether there is an abnormal sheathing in the loom. If so, generate a rapier obstacle avoidance path according to the preset rapier obstacle avoidance algorithm to adjust the rapier movement trajectory; otherwise, proceed with the weaving normally according to the preset process.

2. The method as described in claim 1, characterized in that, The step involves performing anomaly detection on image data and fiber optic signals with the same timestamp according to a preset detection algorithm, and obtaining detection results, including: The intelligently processed image data is inspected, and images that meet preset features in the detection results are identified as abnormal images. The optical fiber signal is filtered, and signals whose light intensity attenuation after filtering is greater than a preset threshold are identified as abnormal signals.

3. The method as described in claim 2, characterized in that, The step of detecting the intelligently processed image data and determining that images meeting preset characteristics in the detection results are abnormal images includes: The upper and lower boundaries of the opening are located based on the edge feature matching algorithm, and an adaptive rectangular detection area that changes with the shape of the opening is generated. The image data within the rectangular detection area is filtered and denoised, and the processed data is converted into a binary image by adaptive threshold segmentation to separate the abnormal yarn from the background. The binary image is subjected to connected component analysis according to a preset function, and the geometric and morphological features of the interconnected pixel regions in each binary image are calculated based on the analysis results. Based on preset abnormal features, all calculation results are identified, and images that match the abnormal features are determined to be abnormal images.

4. The method as described in claim 2, characterized in that, The process of determining whether the loom has any abnormal sheathing based on the test results includes: Determine if there are any abnormal images or signals at the same timestamp. If so, determine if the loom has an opening abnormality; otherwise, determine if the loom does not have an opening abnormality.

5. The method as described in claim 3, characterized in that, The step of generating a sword pole obstacle avoidance path according to a preset sword pole obstacle avoidance algorithm to adjust the sword pole movement trajectory includes: The rectangular detection region of the abnormal image is mapped to a preset spatial coordinate system, and the mapped region is marked as an obstacle region; wherein, the spatial coordinate system is obtained by discretizing the motion plane of the sword. The current position of the sword shaft is taken as the starting point of the path, and the safe end point of the latitude guide is taken as the target point of the path. The A-StarAlgorithm is input into the obstacle region to obtain the sequence of collision-free shortest path points from the starting point to the target point of the path. Curve fitting is performed on the collision-free shortest path point sequence based on spline curves to obtain a smooth path for tracking the rapier motion mechanism; The difference between the real-time position of the sword stick and the smooth path is determined by the PID controller, and a control quantity is output to the servo driver based on the difference to adjust the movement of the sword stick along the smooth path.

6. The method as described in claim 1, characterized in that, After generating the spar obstacle avoidance path according to the preset spar obstacle avoidance algorithm to adjust the spar movement trajectory, the process also includes: When the scimitar obstacle avoidance algorithm fails to generate an obstacle avoidance path, it determines that the scimitar cannot pass through the opening by moving its position, stops the scimitar's movement, and issues an alarm to await manual intervention.

7. A rapier weft insertion adjustment device based on the detection of sheathed yarn on a loom, characterized in that, The device includes: The acquisition module is used to acquire image data that characterizes the sheath shape of the loom and optical fiber signals that characterize the yarn state in the sheath area of ​​the loom. The detection module is used to perform anomaly detection on image data and fiber optic signals with the same timestamp according to a preset detection algorithm, and obtain the detection results. The obstacle avoidance module is used to determine whether there is an abnormal sheathing of the loom based on the detection results. If so, it generates a rapier obstacle avoidance path according to the preset rapier obstacle avoidance algorithm to adjust the rapier movement trajectory; otherwise, it carries out weaving normally according to the preset process.

8. A computer device, characterized in that, The computer device includes a memory and a processor. The memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory to implement the steps of the method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, implements the steps of the method described in any one of claims 1-6.

10. A computer program product, characterized in that, Includes a computer program, which, when executed by a processor, implements the steps of the method according to any one of claims 1-6.

Images