480 results about "Textile industry" patented technology

The invention discloses a textile product defect detection method and system, and the method comprises the steps: collecting a textile surface image, and carrying out the preprocessing; constructing a feature extraction model, and extracting multi-modal features of the textile fabric surface defects; analyzing the extracted features, and classifying defect types; positioning defect positions, and marking defect areas and types; and outputting a defect detection report, and optimizing model parameters according to a detection result. Through multi-modal feature extraction and a feedback optimization mechanism, the classification accuracy and the positioning precision of textile fabric defect detection are remarkably improved, and particularly, the method has outstanding performance in detection of complex and low-contrast defects. According to the invention, the detection efficiency is greatly improved, false detection and missing detection are reduced, and an efficient and intelligent solution is provided for quality control of the textile industry.

The invention discloses an intelligent textile production line control method and system, and relates to the technical field of industrial automation, and the method comprises the steps: collecting operation data in a textile production process in real time, and carrying out the data preprocessing; dynamically adjusting process parameters of the textile production line based on the preprocessed data; detecting the quality state in the textile production process in real time, and adjusting the operation of the production line based on the detection result; constructing a multi-feature fusion fault prediction model, and predicting the operation state of the production line equipment; potential faults are recognized in advance according to prediction results, and the operation mode of the production line is adjusted. The method combines multi-feature fusion analysis, dynamically optimizes the equipment operation state, identifies and adjusts potential faults in advance, improves the production quality and efficiency, reduces the maintenance cost and the shutdown risk, is significantly superior to a traditional method, and provides powerful technical support for intelligent upgrading of the textile industry.

The invention discloses an electronic jacquard machine control method and system based on multi-channel collaboration, and the method comprises the steps: calculating a delay compensation value of each channel in real time according to the hardware performance difference and signal transmission delay data of each channel, and dynamically adjusting the time sequence offset of a control instruction of an electronic jacquard machine by using the delay compensation value, generating a multi-channel cooperative control signal; according to input fabric pattern data, decomposing the fabric pattern data to generate a layered instruction set, and binding the layered instruction set to a multi-channel cooperative control signal to form a time-space synchronization instruction set; according to channel operation state data acquired in real time, identifying an abnormal channel and a fault type thereof, and generating a reconstruction instruction set after fault immunization; and dynamically allocating computing resources and storage bandwidth according to the reconstruction instruction set, generating an optimization execution instruction set, and issuing the optimization execution instruction set to each channel for execution in real time. By utilizing the embodiment of the invention, the control capability of the electronic jacquard machine and the fabric production efficiency can be improved, and the intelligent development of the textile industry is promoted.

The invention discloses a fiber raw material traceability method and monitoring system based on big data, and the method comprises the steps: collecting the multi-source data of a raw material through an Internet of Things device, including image data, sensor data and a unique identity; performing standardization processing on the collected data, and combining to generate a comprehensive feature vector; inputting the comprehensive feature vector into an improved convolutional neural network, and outputting parameters of the fiber raw material, including crimpness, length, color feature, region and generation time; the traceability information is encrypted and stored through a block chain technology; a user retrieves and displays fiber raw material parameters in real time through the query module. By introducing the big data analysis and block chain technology, the problems of data splitting, easy tampering and insufficient intelligence in the existing fiber raw material traceability and quality monitoring method are solved, the traceability transparency, data security and monitoring efficiency are significantly improved, and the method is suitable for supply chain management and quality control in the textile industry.

The invention discloses an enterprise order collaborative manufacturing scheduling optimization method and system based on improved SPSA. The enterprise order collaborative manufacturing scheduling optimization method based on the improved SPSA comprises the following steps: constructing a network collaborative scheduling model; determining constraint conditions of the network collaborative scheduling model; solving the network collaborative scheduling model by adopting an improved SPSA scheduling algorithm; and generating a scheduling scheme of an optimal solution. According to the method, an order is divided into a plurality of sub-tasks, then a network collaborative scheduling model is constructed, the model is solved through an improved SPSA-based scheduling algorithm, a scheduling scheme of an optimal solution is generated, the order is allocated to a proper enterprise, and an order production task is completed collaboratively. According to the method, resources between enterprises can be dispatched in a coordinated manner, the overall production efficiency and the product quality are improved, waste and repeated configuration of the resources can be avoided, and the research blank of application of small and medium-sized enterprises in the textile industry at home and abroad can be filled up.

The invention provides a textile industry broken yarn identification method and system based on a neural network, and the method comprises the steps: collecting yarn multi-modal data, including a surface image, a fracture sound wave signal and tension change data; preprocessing the data, and extracting an image ROI region, sound wave spectrum features and a tension mutation sequence; performing space-time alignment and feature extraction on the extracted content to obtain a joint feature vector; inputting the broken yarn into a trained broken yarn identification model, wherein the model can identify broken yarn features; judging whether broken yarns exist or not according to the output result and outputting an identification result; and updating the model through online incremental learning. According to the method, multiple types of data are combined, the adaptive preprocessing and feature extraction technology is used, environmental noise is inhibited, key features are focused, and the problem of false alarm of a traditional sensor is solved; multi-modal features are fused through space-time alignment and a self-attention mechanism, and bidirectional LSTM modeling is combined, so that a broken yarn dynamic rule is accurately captured, and the problems of missing detection and delay of manual inspection are avoided.

The invention discloses a yarn weak twist and hairiness intelligent detection system based on visual stroboscopic synchronization, particularly relates to the field of quality control in the textile industry, is used for solving the problem of accurate detection of weak twist and hairiness defects in the yarn production process, and dynamically adjusts the flash frequency of a stroboscope according to the real-time speed and acceleration data of yarn, so that the detection accuracy is improved. The light source and the yarn are ensured to move synchronously, and a high-resolution image is obtained. In combination with yarn motion spectrum analysis and image quality evaluation, a complexity score and a matching degree score are generated and are used for dynamically regulating and controlling image noise reduction and edge detection parameters, and characteristic extraction requirements under different yarn motion conditions are met. The weak twist characteristic and the hairiness texture of the yarn are accurately extracted through a multi-scale edge detection and wavelet transform algorithm, a twist distribution model is constructed, the boundary range is corrected in combination with hairiness distribution data, characteristic interference is reduced, and the detection precision and reliability are improved.

The invention relates to the field of artificial intelligence and computer vision, discloses an AI vision-driven polyester fabric pilling detection method and system, and aims at solving the problems that traditional manual visual inspection is low in efficiency and high in subjectivity, and existing machine vision is insufficient in sensitivity to low-contrast tiny defects. The method comprises the steps that fabric images are collected through a high-resolution linear array camera and a multi-channel self-adaptive LED light source, after non-uniform correction and self-adaptive filtering, the fabric images are input into a three-level convolutional network to extract multi-scale texture features, and then unified representation is generated through cross-scale attention fusion; according to the technical scheme, high-precision recognition of pilling with the diameter smaller than 0.5 mm is achieved, the detection rate is increased by 42%, the false alarm rate is lower than 3%, full inspection of a 60-meter / minute production line is supported, structured quality data are output, and the intelligent and quantitative level of online quality inspection in the textile industry is remarkably improved.

The invention relates to the technical field of textile industry, and discloses a textile production equipment recommendation scheduling method, which comprises the following steps: S1, extracting production process information: before scheduling, firstly extracting process information of a product to be produced from an order system; s2, obtaining candidate equipment information: after the production process information is obtained, extracting detailed information of all available equipment from an equipment management system; s3, judging a forced constraint condition; s4, multi-dimensional matching of priority conditions is carried out; s5, calculating the matching degree of the raw materials; s6, matching the opening value of the equipment; s7, scheduling optimization is carried out; and S8, generating a scheduling scheme. Through fine matching of process parameters and equipment parameters, the selected equipment can be ensured to be most suitable for the current production task, the equipment adjustment time and the production preparation time are reduced, so that the production efficiency is improved, the use of the equipment can be reasonably arranged, the downtime caused by frequent switching of the equipment or the process is reduced, and the production efficiency is improved. The continuous production capacity is improved.

The invention relates to the technical field of wind tunnel experiments and textile carding, and discloses a guide plate system for a card clothing test wind tunnel and a test method thereof, the system comprises a mounting clamp, a guide plate, a driving mechanism and a tail airflow measurement and analysis system; the guide plate is located in the wind tunnel, forms a sealing structure with the inner wall surface of the test section of the wind tunnel, and is continuously controlled to move along the direction vertical to the test airflow through the driving mechanism; the length of the wind tunnel is 200-1000 mm, the height of the wind tunnel is 10-150 mm, and the width of the wind tunnel The guide plate is provided with static pressure measuring points which are continuously arranged; card clothing is arranged below the flow guide plate and is arranged on the mounting clamp; the mounting fixture is arranged on the bottom surface in the wind tunnel; an airflow measurement and analysis system is arranged behind the flow guide plate and installed on the inner bottom face of the wind tunnel. The actual carding process in the textile industry is simulated, the optimal numerical values of the gauge, the needle shape, the carding airflow and other characteristics in the experiment are determined, and the test precision of the wind tunnel is improved.

The invention provides a cloth defect detection method and device and a readable storage medium. The method comprises the following steps: acquiring a cloth image; carrying out image feature extraction and quantitative analysis processing on the basis of the cloth image to obtain a periodic rule of a pattern in the cloth image; splicing the cloth image according to the periodic rule of the pattern in the cloth image, and determining a corresponding template image according to the obtained spliced image; and performing template comparison detection according to the spliced image and the corresponding template image to obtain a cloth defect detection result. Through an efficient algorithm and an advanced image analysis technology, the problems that the manual quality inspection efficiency is low, the omission ratio is high and the detection precision of the cloth with the complex patterns is insufficient in the textile industry are powerfully solved, the quality inspection efficiency is greatly improved, the omission ratio is remarkably reduced, and high-precision detection of the cloth with the complex patterns is achieved.

The invention relates to the technical field of mechanical fault diagnosis, in particular to a multi-sensor fusion textile machinery fault diagnosis method, which comprises the following steps of S1, capturing a vibration signal, a sound waveform and a visual image in equipment operation; s2, executing preprocessing operation on the data collected in the S1; s3, integrating heterogeneous data of vibration, sound and vision to generate comprehensive high-dimensional feature representation; s4, performing fault feature extraction and classification by using a preset AGNN; s5, when the AGNN identifies a specific fault type, automatically generating a detailed fault report; and S6, continuously optimizing the DMFN model and the AGNN model by using the feedback information. According to the invention, by combining DMFN and AGNN technologies, efficient, accurate and comprehensive diagnosis of textile machinery faults is realized, the fault early warning capability is significantly improved, the maintenance process is optimized, and powerful support is provided for intelligent development of the textile industry.

The invention discloses an intelligent speed regulation training method and system for a high-speed jet color loom, and belongs to the field of textile industry automation. The technical problem that a traditional high-speed jet color loom is low in production efficiency is solved. According to the technical scheme, accurate process control and automatic adjustment are achieved at different weaving and printing speeds through a multi-parameter real-time monitoring system and an intelligent speed regulation control module of the high-speed jet color weaving machine on the basis of a self-adaptive weaving and printing parameter regulation and intelligent feedback mechanism in combination with a comprehensive strategy of multi-parameter simulation, quality evaluation and defect detection; comprising the following steps: inputting an order and a pattern, determining a strategy according to analysis characteristics, calculating multivariable weights to adjust the overall speed of the fabric, automatically prompting speed regulation parameters to carry out threshold alarm, adaptively adjusting the speed to match the real-time change of multiple parameters, and identifying the defects of the fabric based on a color CLE Lab model. Dynamically adjusting the weaving and printing speed and generating a report according to a defect detection result; the invention is applied to the high-speed jet color weaving machine.

The embodiment of the invention discloses an automatic distribution method and device for multi-variety and multi-frequency weft yarns in the home textile industry. The method comprises the steps of obtaining a weft yarn production order; performing analysis and demand prediction on the weft yarn production order to obtain a prediction result; analyzing the inventory of the weft yarns to obtain an analysis result; determining a distribution scheme according to the prediction result and the analysis result; and a distribution path is optimized according to the distribution scheme, and automatic distribution is carried out. By implementing the method provided by the embodiment of the invention, the delivery efficiency can be improved, human errors can be reduced, and the production response speed and flexibility can be improved.

The invention discloses a single-component polyurethane liquid glue which comprises a hydroxyl-terminated polyurethane prepolymer, polyol and isocyanate, and the molar ratio of an isocyanate group to a hydroxyl group is (1.01-5): 1; the hydroxyl-terminated polyurethane prepolymer comprises aliphatic or / and alicyclic isocyanate and polyol, and the molar ratio of an isocyanate group to a hydroxyl group is (0.5-0.99): 1. The preparation method comprises the following steps: firstly, synthesizing a hydroxyl-terminated polyurethane prepolymer, and then taking the hydroxyl-terminated polyurethane prepolymer as a main material to react with a small part of polyhydric alcohols and isocyanate. The polyurethane liquid adhesive synthesized by the two-step method has the performance advantages of high initial adhesion and low hardness, meets the process requirement of normal-temperature coating, can replace an adhesive film product and a hot melt adhesive product, and is applied to composite bonding of fabrics in the textile industry.

The invention relates to the technical field of intelligent control of an air-jet vortex spinning yarn-forming process in the textile industry, in particular to an air-jet vortex spinning yarn-forming process control model based on a semi-supervised stacked auto-encoder, which comprises the following steps of: (1) analyzing data hidden variable distribution by adopting a Gaussian mixture model, and marking unlabeled data to expand data resources; (2) constructing a semi-supervised auto-encoder, and synchronously realizing data reconstruction and multi-quality characteristic'balance point 'prediction through weight sharing design; (3) stacking layer by layer to form a depth model, and strengthening multi-characteristic correlation modeling; and (4) realizing automatic disturbance detection in combination with a sequence auto-encoder containing an LSTM layer, an attention mechanism and a Tukey rule. The model reduces data dependence, improves the quality stability of resultant yarn and the anti-interference performance of production, adapts to industrial intelligent requirements, and assists the application upgrade of the air-jet vortex spinning technology.

The utility model discloses and provides a dye mixing device which comprises a mixing stirrer, a supporting plate is fixedly installed on one side of the mixing stirrer, a vacuum pump is fixedly installed on the outer surface of the top end of the supporting plate, one end of the vacuum pump is connected with an exhaust pipe, and one end of the exhaust pipe is connected with the mixing stirrer. One end of the vacuum pump is connected with an exhaust pipe, the other end of the vacuum pump is connected with a connecting pipe, one end of the connecting pipe is connected with a gas collecting tank, and the top end of the gas collecting tank is provided with a gas release pipe. The bubble removing effect is remarkably improved, the influence of bubbles on the dye mixing uniformity is avoided through bubble removal, it is guaranteed that the quality of the mixed dye is higher, and the strict requirements for dye mixing in the textile industry, the printing industry, the coating industry and other industries are met.

The utility model discloses automation equipment for silk coil feeding, which relates to the technical field of textile industry and comprises an unstacking station and an automatic carrying trolley, guide rails are arranged on the front end face and the rear end face of the top of a frame, and a supporting frame is vertically arranged in the middle of an inner cavity of the frame. Matched automatic carrying trolley material taking points are arranged between the left side of the supporting frame and the left side of the inner cavity of the frame, and an electric control cabinet is arranged on the left side of the frame. Manual work is replaced by a machine; according to the automatic wire coil feeding device, traditional manual operation is replaced with mechanical automation, the production efficiency can be remarkably improved, quality control in the wire coil feeding process can be guaranteed, in a wire coil storage area, neatly-arranged wire coils wait to be treated, then two sets of automatic clamping jaws are arranged, and the automatic wire coil feeding device is used for feeding the wire coils. The first four-degree-of-freedom clamping jaw and the second four-degree-of-freedom clamping jaw work cooperatively, the wire coil is carried to a material taking point of the automatic carrying trolley from a storage area, and the automatic carrying trolley appears on time at the point and prepares to take materials.

The invention discloses a textile industry waste silk recycling and feeding device, and relates to the technical field of waste silk recycling, the textile industry waste silk recycling and feeding device comprises a base, the upper surface of the base is provided with a main baffle and an auxiliary baffle, the upper surface of the base is further provided with a main conveying transmission belt and an auxiliary conveying transmission belt, and the upper surface of the main baffle is fixedly provided with a feeding port; a plurality of combing rollers and a bearing mechanism are further arranged on the upper surface of the auxiliary conveying belt, the bearing mechanism comprises two fixing boxes, a signal processor and a brake motor are arranged on the surfaces of one sides of the two fixing boxes correspondingly, a weighing frame is arranged between the two connecting shafts, the bearing mechanism further comprises a plurality of supporting assemblies, and the supporting assemblies are arranged on the supporting assemblies. The supporting assembly comprises a fixing table, a sliding wheel groove is formed in the upper surface of the fixing table, in the scheme, by arranging the bearing mechanism, the cleaning mechanism and the anti-knotting mechanism, the probability that waste wires are accumulated and wound on the edge of the conveying belt is reduced, and the conveying efficiency is further improved.

The invention relates to the technical field of automatic control in the textile industry, and discloses an automatic control system of a doffer, which comprises a sensing module, a decision control module, an execution module, an energy consumption management module and a fault monitoring and maintenance module. Through a multi-dimensional data acquisition and intelligent control technology, each link of operation of the doffer can be comprehensively covered, conventional mechanical action execution is concerned, factors such as spindle posture, yarn tension, equipment energy consumption and vibration state are also included, and an intelligent algorithm is deeply integrated to carry out working condition analysis and instruction generation; doffing control can meet production requirements more accurately, and powerful support is provided for efficient development of doffing operation.

The invention provides a spatial feature fused colored spun yarn color characterization method, and the method comprises the steps: constructing a multi-level architecture of 1D-CNN time sequence feature extraction, DNN aperture internal fusion, Bi-LSTM spatial sequence modeling, ResNet image color feature extraction, pyramid pooling layer image spatial feature extraction, and Transform cross-modal fusion through five aperture multi-position spectrum collection. The method is characterized by comprising the steps of hierarchical feature extraction of a multi-aperture spectrum, bidirectional LSTM space dependence modeling and Transform spectrum depth fusion. Experiments show that the method is obviously superior to the prior art in color prediction precision, material generalization and calculation efficiency, and is suitable for intelligent color control and formula design in the textile industry.

The invention relates to the technical field of agricultural biology, in particular to a glucose oxidase mutant AhGODA-M1, a coding gene and application thereof, and a method for improving enzymatic characteristics of glucose oxidase. According to the invention, T72R and A153P site-directed mutagenesis is carried out on 72th and 153th amino acids of glucose oxidase AhGODA with an amino acid sequence as shown in SEQ ID NO: 1. The enzyme activity of the mutant is improved from 112 U / mg to 166 U / mg, and the improvement amplitude is 48%; the optimum temperature is increased from 40 DEG C to 50 DEG C; after treatment at 70 DEG C for 30 min, about 33% of residual activity is reserved, the application requirements in the fields of food, feed, textile industry and the like can be better met, and the method has very wide application prospects.

The invention provides a dynamic feature contribution degree-based color textile fabric image retrieval method. Innovation and improvement are carried out aiming at single feature limitation and fixed weight fusion defects existing in a traditional retrieval technology. Color, texture and shape features are separated through a multi-modal feature decoupling technology, and coupling interference between the features is eliminated; a dynamic contribution degree quantification mechanism is innovatively constructed, gradient back propagation is used for calculating the contribution proportion of features to retrieval results in real time, and weight self-adaptive adjustment is achieved. According to the method, the problem of retrieval deviation caused by complex characteristics such as color gradient and blending structure difference of the colored spun yarn fabric is solved in a breakthrough mode, weight distribution can be intelligently matched according to inquired image characteristics (for example, the color gradient fabric focuses on color characteristics, and the jacquard fabric focuses on shape edges), and the retrieval result better fits human visual perception. According to the technical scheme, the image retrieval precision of complex fabrics in the textile industry is effectively improved, and an intelligent solution is provided for production process data association.

The invention discloses an intelligent evaluation method suitable for the shrinkage rate of a complex pattern fabric. The method comprises the following steps: (1) acquiring a fabric image; (2) preprocessing the fabric image; (3) model design: designing an enhanced deep neural network target detection algorithm model which comprises a small target detection layer, a multi-scale attention module and a bidirectional feature pyramid network structure, and replacing a loss function with an MPDIOU regression loss function; (4) model training; and (5) detecting the shrinkage rate of the fabric: visually displaying the position of the mark point on the fabric image, and then calculating the position change of the mark point of the fabric image before and after washing to obtain the shrinkage rate. According to the invention, the shrinkage rate of the textile fabric before and after the treatment flows of washing, drying, ironing and the like can be accurately measured, the identification, measurement and data recording of sample marks can be automatically completed, the interference of human factors is reduced, and the detection speed and accuracy are improved, so that the quality detection requirements of the textile industry are better met.

The invention relates to the technical field of production raw material dehydration equipment, and provides a mud pressing machine for the textile industry, which comprises a rack, and a sliding main beam extending along the length direction is arranged on the rack; the number of the filter plates is multiple, two sliding supporting assemblies are symmetrically arranged on the two sides of each filter plate in the width direction of the filter plate in a sliding mode, and the multiple filter plates are arranged on the sliding main beam in a sliding mode through the sliding supporting assemblies; the bottom and the side part of the sliding support assembly are respectively and correspondingly propped against the top and the side edge of the sliding main beam in a sliding manner, and the sliding support assembly is configured in a manner that after the filter plate deflects along the vertical direction by the deflection shaft, the side wall of the sliding support assembly is extruded with the side edge of the sliding main beam, and then the sliding support assembly is driven to slide in a direction far away from the filter plate; the device is used for reducing extrusion force between the side wall of the sliding supporting assembly and the side edge of the sliding main beam. According to the technical scheme, the technical problem that the main beam is scratched or deformed in the filter pressing working process of the plate-type membrane filter press in the prior art is solved.

The invention relates to the technical field of textile industry, in particular to a textile fabric winding tension prediction system based on machine learning, which comprises an environment sensing module, a dynamic data acquisition module, a data preprocessing enhancement module, a deep learning model training module, a self-adaptive control module and a fault diagnosis early warning module. Wherein the environment sensing module is used for monitoring spinning environment data in real time; the dynamic data acquisition module is used for comprehensively monitoring the running state and the physical environment change of the textile machinery; the data preprocessing enhancement module is used for standardizing the data acquired by the acquisition module; and the deep learning model training module is used for carrying out model training on tension change in the textile fabric winding process. According to the invention, real-time and accurate tension control is realized, the production automation and intelligence levels are improved, and fault diagnosis early warning is started, so that the production efficiency and quality of textiles are remarkably improved, and meanwhile, the resource waste and the production cost are reduced.

The invention provides alkaline laccase WCotA and application thereof, and belongs to the technical field of biological engineering. According to the invention, assumed protein codons from bacillus amyloliquefaciens are optimized by a bioengineering technology, then are heterologously expressed on a carrier, and are transferred into escherichia coli with clear genetic background and fast growth cycle for amplification and expression to obtain a protein product; the amino acid sequence of the protein product is as shown in SEQ ID NO.1, and the nucleotide sequence for coding the protein product is as shown in SEQ ID NO.2; according to the present invention, the characterization results show that the protein product has high laccase activity, and is marked as alkaline laccase WCotA; the alkaline laccase WCotA has the outstanding advantages of alkali resistance, high temperature resistance, wide pH action range and the like, and has good application in the fields of textile industry, food processing, pulping processing, industrial wastewater treatment and the like.

The utility model discloses a finished textile product conveying device for the textile industry. The finished textile product conveying device comprises a shell and a self-cleaning mechanism. A rotating groove is formed in the upper end of the shell, conveying rollers are rotationally connected between the front inner wall and the rear inner wall of the rotating groove through rotating shafts, the two conveying rollers are in transmission connection through a conveying belt, a conveying motor is arranged on the rear side face of the shell, the front end of an output shaft of the conveying motor is fixedly connected with a rotating shaft of the conveying roller on the left side, and a control switch set is arranged on the front surface of the shell. The input end of the control switch group is electrically connected to an external power supply; the input end of the conveying motor is electrically connected to the output end of the control switch group; according to the finished textile product conveying device for the textile industry, dust on the surface of the conveying device is automatically cleaned, the cleaned dust can be automatically collected, accumulation of the dust on the surface of a cleaning component is reduced, the cleaning effect is improved, a clean environment is provided for conveying of finished textile products, and the conveying efficiency is improved. And the quality of textile production is ensured.

The invention discloses a vortex spinning yarn defect detection method and system based on computer vision, and relates to the technical field of textile industry quality control and image recognition, and the method comprises the steps: obtaining a bright field image sequence and a dark field image sequence, and collecting a yarn position signal and an air pressure pulsation signal of a spindle vortex field; performing track modeling and inter-frame displacement compensation on the bright field image sequence to generate a yarn structured displacement image; constructing an airflow fiber-carrying feature map; performing spatial registration and fusion on the yarn structured displacement image and the airflow fiber-carrying feature map to obtain a dual-channel feature map; generating a defect cause directivity judgment instruction; marking a defect position based on defect information of the defect cause directivity judgment instruction, and generating a process parameter adjustment suggestion signal; and constructing a defect-process feedback sample set. The air vortex spinning yarn defect detection system effectively solves the key problems that an existing air vortex spinning yarn defect detection system is single in detection dimension, defect causes cannot be distinguished, and real-time process closed-loop feedback is lacked.

The invention relates to the technical field of textile industry, and discloses a textile dust collecting device for textile equipment, which comprises a collecting box and universal wheels, a filtering mechanism is arranged in the collecting box, the filtering mechanism comprises a fixing plate, a sliding rod, a mounting plate, a filter screen and a moving rod, one side of the fixing plate is fixedly connected with one end of the sliding rod, and the other side of the fixing plate is fixedly connected with the mounting plate. The outer wall of the sliding rod is slidably connected with the inner wall of a mounting plate, the inner side of the mounting plate is fixedly connected with the two ends of a filter screen, one side of the mounting plate is fixedly connected with one end of a moving rod, the other end of the moving rod is fixedly provided with an extrusion plate, and the outer wall of the extrusion plate is slidably connected with a piston box. The textile dust collecting device is simple in structure and convenient to use, can effectively prevent the filter screen from being blocked, solves the problem that in actual use, the filter screen can be blocked after being used for a long time, so that filtering and collecting cannot be conducted, and improves the working efficiency.