Foreign Fibers Research Articles

Content Estimation of Foreign Fibers in Cotton Based on Deep Learning

Cotton foreign fibers directly affect the quality of a textile product; the less foreign fibers in raw cotton, the higher the quality grade of the textile product. Based on the foreign fiber clean machine, this paper proposed an evaluation method of foreign fiber content using deep learning. First of all, a large number of images of foreign fibers were collected from different production lines and annotated to obtain the mask image dataset of foreign fibers. Secondly, by comparing the image segmentation algorithm based on deep learning, tests showed that U-Net has a better performance on different segment metrics evaluations, and U-Net is improved to realize the real-time segmentation of foreign fiber images. The actual size of the foreign fiber could be calculated through the combination of the segment result and the mechanical parameters of the machine. Finally, the test results showed that the relative error between the estimated size and the actual size was less than 4%. After the prototype test, the algorithm was deployed on the actual production line and, by comparing the algorithm data in a random time with the actual foreign fiber statistical data, the overall error was less than 2%. The test showed that the new evaluation method can fully reflect the content of foreign fiber in raw cotton.

改进Faster RCNN模型在棉花异性纤维识别中的应用

改进Faster RCNN模型在棉花异性纤维识别中的应用

Detection of foreign fiber in cotton based on improved YOLOv3

Detection of foreign fiber in cotton based on improved YOLOv3

Classification of foreign fibers using deep learning and its implementation on embedded system

In recent years, the foreign fibers in cotton lint significantly affect the quality of the final cotton textile products. It remains a challenging task to accurately distinguish foreign fibers from cotton. This article proposes an embedded system based on field programmable gate array (FPGA) + digital signal processor (DSP) to recognize and remove foreign fibers mixed in cotton. With substantial tests of this system, we collect massive samples of foreign fibers and fake foreign fibers. Based on these samples, a convolution neural network mode is developed to validate the classification of the suspected targets from the detection subsystem, to improve the detection reliability. After training several model architectures, we find a model with the best balance between performance and computation. The high success rate (up to 96% in the validation set) demonstrates the effectiveness of the model. Moreover, the computation time (5 ms on a single image based on an eight-core DSP) indicates the efficiency of the detection, which ensures the real-time application of the system.

Foreign Fiber Detection in Cotton using HSI Approach for Industrial Automation

Foreign Fiber Detection in Cotton using HSI Approach for Industrial Automation

Efficient detection method for foreign fibers in cotton

Since foreign fibers in cotton seriously affect the quality of the final cotton textile products, machine-vision-based detection systems for foreign fibers in cotton are receiving extensive attention in industrial equipment. As one of the key components in detection systems, the suitable and good classifier is significantly important for machine-vision-based on detection systems for foreign fibers in cotton due to it improving the system’s performance. In the study, we test five classifiers in the dataset of foreign fibers in cotton, and for finding the best feature set corresponding to the classifiers, we use the four filter feature selection approaches to find the best feature sets of foreign fibers in cotton corresponding to specific classifiers. The experimental results show that the extreme learning machine and kernel support vector machines have the excellent performance for foreign fiber detection and the classification accuracy are respectively 93.61% and 93.17% using the selected corresponding feature set with 42 and 52 features.

异纤计量系统皮棉开松机构的研制

异纤计量系统皮棉开松机构的研制

Detection clustering analysis algorithm and system parameters study of the near-point multi-class foreign fiber

In this paper, we investigate a detection algorithm for foreign fiber during the processing of cotton textile. By collecting a large number of samples, we determine the color model and establish its characteristic parameters of a foreign fiber. We found foreign fibers of multiple types (classes) and proposed a classification–recognition algorithm based on clustering analysis. The maximum error of the studied recognition algorithm is 0.012, which meets the requirement to recognize foreign fibers. Through many experiments, the optimal parameters for the foreign fiber detection system were determined, and the fiber recognition rates for different types were obtained. The lowest recognition rate is 85%. This is sufficiently high to reject foreign fibers and reach the standards of the textile industry. Experimental results show that foreign fiber clustering analysis algorithm is feasible, and it not only improves the quality of foreign fiber detection significantly, but also has high theoretical value and practical value.

Effectiveness of Various Reinforcing Materials for Fabricating High-Pressure-Vessel Shells

The physicomechanical characteristics of modern reinforcing materials of various chemical natures were compared. Results of destructive tests of shells based on aramid and carbon fibers were presented. It was shown that shells of limited mass fabricated with Rusar-S-test reinforcing material had destruction pressures greater than those of carbon-plastic analogs based on the best foreign carbon fibers.

An Efficient and Effective Automatic Recognition System for Online Recognition of Foreign Fibers in Cotton

Preventing foreign fibers from being mixed with cotton is essential for producing high-quality cotton textile products. It remains a challenging task to accurately distinguish foreign fibers from cotton. This paper proposes an efficient recognition system to accurately recognize foreign fibers mixed in cotton. The core component of the proposed system is an efficient classifier based on the kernel extreme learning machine (KELM). A two-step grid search strategy, which integrates a coarse search with a fine search, is adopted to train an optimal KELM recognition model. The resultant model is compared with the support vector machine and extreme learning machine on a real data set using tenfold cross-validation analysis. The experimental results show that the proposed recognition system can achieve classification accuracy as high as 93.57%, which is superior to the other two state-of-the-art systems. The results clearly confirm the superiority of the developed model in terms of classification accuracy. Promisingly, the proposed system can serve as a new candidate of powerful foreign fiber recognition systems with excellent performance.

Numerical simulation of the air flow field in the foreign fiber separator

The air flow field of a foreign fiber separator is simulated numerically. Effects of design parameters such as the nozzle diameter and entrance width of the noil box on the air velocity along nozzle axis, turbulence intensity, and jet deflection distance are studied. Larger nozzle diameters and larger entrance widths of the noil box are advantageous to the elimination of foreign fibers. The results provide a theoretical basis for the design of foreign fiber separators.

A two-stage feature selection method with its application

Foreign fibers in cotton seriously affect the quality of cotton products. Online detection systems of foreign fibers based on machine vision are the efficient tools to minimize the harmful effects of foreign fibers. The optimum feature set with small size and high accuracy can efficiently improve the performance of online detection systems. To find the optimal feature sets, a two-stage feature selection algorithm combining IG (Information Gain) approach and BPSO (Binary Particle Swarm Optimization) is proposed for foreign fiber data. In the first stage, IG approach is used to filter noisy features, and the BPSO uses the classifier accuracy as a fitness function to select the highly discriminating features in the second stage. The proposed algorithm is tested on foreign fiber dataset. The experimental results show that the proposed algorithm can efficiently find the feature subsets with smaller size and higher accuracy than other algorithms.

Research of foreign fibers in cotton yarn defect model based on regression analysis

The detecting of foreign fiber may not be very effective, particularly around the detection zone where many types of foreign fibers may coexist. In order to eliminate the fibers more effectively, a model has been established to detect foreign fiber faults in yarn. Relevant data were collected through investigation of a number of standard samples, with the length and area of foreign fibers as the independent variables, and the number of defects as the dependent variable, which were combined using linear regression theory to establish a regression equation for different fiber defects. The equations to find the regression coefficients, which include the model fitting degree, the Durbin–Watson value, the standard error, and the Cook distance, were rigorously tested, and the regression equation was eventually compiled to produce the yarn faults model. When the fiber detection equipment recognizes fibers with a foreign profile, the calculated profile fiber size is used in a corresponding regression equation which obtains the defect points and compares them with each other, so that foreign fibers which are potentially more dangerous can be identified and preferentially eliminated. In order to verify the model, spinning experiments are performed. The actual defects from the experiment are compared with the predicted theoretical defects from the equation, and the prediction accuracy was found to reach more than 95%, showing that the foreign fiber yarn faults model, which lays a theoretical foundation for foreign fiber detection, is accurate and effective.

A fast image segmentation algorithm for detection of pseudo-foreign fibers in lint cotton

Detection of pseudo-foreign fibers based on Automatic Vision Inspection system is crucial to improve the classification accuracy of foreign fibers in cotton, and justify the quality and grade of lint. Pseudo-foreign fibers are dried cotton leaves, seed-coats, barks, grass and dust which mixed into cotton during production, they usually have relative small sizes and large quantities compared to the foreign fibers, so it is hard to detect and segment them from images. In this paper a novel algorithm is proposed to solve the problem. 110 images with pseudo-foreign fibers are tested, and the result showed that both spots and slender shaped pseudo-foreign fibers can be segmented clearly with average speed of 0.67s, which can meet the requirement of online cotton trash detection.

Foreign Fiber Image Segmentation Based on Maximum Entropy and Genetic Algorithm

In machine-vision-based systems for detecting foreign fibers, due to the background of the cotton layer has the absolute advantage in the whole image, while the foreign fiber only account for a very small part, and what’s more, the brightness and contrast of the image are all poor. Using the traditional image segmentation method, the segmentation results are very poor. By adopting the maximum entropy and genetic algorithm, the maximum entropy function was used as the fitness function of genetic algorithm. Through continuous optimization, the optimal segmentation threshold is determined. Experimental results prove that the image segmentation of this paper not only fast and accurate, but also has strong adaptability.

Research on Destriping Based on Rough Set

In order to remove the stripe noises in cotton foreign fiber images by line scanning camera collected, in multi threshold segmentation of rough set, every region’s color is instead of the statistics color of the region. This method can retain the detail information of original image as far as possible, and do well in the stripe noise removal. The roughness of rough set was calculated respectively using directional diagram, Canny operator and Sobel operator. Comparing the three methods, the results indicate that the Canny operator keeps the more details of image, and directional diagram and Sobel operator have the better effects on denoising.

Feature selection based on improved ant colony optimization for online detection of foreign fiber in cotton

Feature selection plays an important role in the machine-vision-based online detection of foreign fibers in cotton because of improvement detection accuracy and speed. Feature sets of foreign fibers in cotton belong to multi-character feature sets. That means the high-quality feature sets of foreign fibers in cotton consist of three classes of features which are respectively the color, texture and shape features. The multi-character feature sets naturally contain a space constraint which lead to the smaller feature space than the general feature set with the same number of features, however the existing algorithms do not consider the space characteristic of multi-character feature sets and treat the multi-character feature sets as the general feature sets. This paper proposed an improved ant colony optimization for feature selection, whose objective is to find the (near) optimal subsets in multi-character feature sets. In the proposed algorithm, group constraint is adopted to limit subset constructing process and probability transition for reducing the effect of invalid subsets and improve the convergence efficiency. As a result, the algorithm can effectively find the high-quality subsets in the feature space of multi-character feature sets. The proposed algorithm is tested in the datasets of foreign fibers in cotton and comparisons with other methods are also made. The experimental results show that the proposed algorithm can find the high-quality subsets with smaller size and high classification accuracy. This is very important to improve performance of online detection systems of foreign fibers in cotton.

Classification Processing Method of Cotton Foreign Fibers Based on Probability Statistics and BP Neural Network

A classification processing method of cotton foreign fibers was proposed based on probability statistics and BP neural network. Due to the origin was wide, the type was complex and the characteristic of cotton foreign fibers was different, it was difficult to build a model on classification and identification of cotton foreign fibers in the detection process of cotton spinning enterprises. This method could solve this question elegantly. Firstly, obtained the sample data by extracting the mean value of R, G, B in the fiber image and built a model about BP neural network. Then, classified 2-types cotton foreign fibers by calculating absolute value and variance of the feature vector based on probability statistics. Finally, processed the extraction features according to the different types image. The cross-validation experiment, the results show that the method combining the probability statistics and BP neural network can classify the cotton foreign fibers efficiently, and the effect is better when the types of cotton foreign fibers corresponding to the different features extraction methods The cross validation experiment, results showed that the combination can effectively identify the classification of foreign fibers and BP network based on probability and statistics, and different types of contton foreign fiber used different feature extraction methods, the effect is remarkable.

Distribution of Cotton in Rectangular Pipeline for Horizontal Foreign Fiber Removed Device

A numerical simulation method using the model of the gas-cotton two-phase is used to analyze the distribution of the cotton in the rectangular pipeline for a horizontal foreign fiber removed device. According to the motion characteristics of the cotton, the optimum length of the rectangular pipeline is found and the distribution of the cotton in the pipeline is obtained. The simulation results show that the optimum length is for the cross-section pipeline. At the same time, in the range of the cotton mainly flows in the middle of the pipeline bottom and the maximum volume fraction of the cotton is 4.5%, at the both sides of the pipeline bottom the cotton is less and the average volume fraction of the cotton is 1%, and there is no the cotton in the middle and upper part of the pipeline; in the range of , the cotton increases rapidly in the middle and upper part of the pipeline and the volume fraction is about 2.7% at ; in the range of , the cotton flows steadily and the volume fractions of the cotton are the same in the middle and upper part of the pipeline, about 2.7% but 1.5% in the lower part of the one. In addition, for the level centers of the cross-sections perpendicular to the cotton flow direction, in the unsteady zone the volume fraction curves of the cotton are symmetrical like a saddle, and in the steady zone the cotton is evenly distributed and its volume fraction curves are horizontal lines.

An Accurate Detection System of Foreign Fibers in Cotton

An Accurate Detection System of Foreign Fibers in Cotton