In the process of textile production, the detection of yarn tension is very important to ensure product quality. In order to detect yarn tension efficiently and conveniently, a non-contact detection method based on transverse frequency was established. Firstly, the governing equation of yarn motion was derived by using the Hamilton principle and solved by the Galerkin truncation method. Then, the natural frequencies of yarns with different linear density were calculated according to the yarn characteristic equation. Finally, the fitting formulas of tension, speed, and frequency of yarn axial motion were derived. By measuring the natural frequency of yarn, the yarn tension could be calculated conveniently and quickly. A high-speed camera was used to measure the transverse vibration displacement of yarn and detect the free vibration frequency of yarn. Through experiments, the results of tension sensor and yarn tension detection based on vibration frequency were compared, and the results show that the error was within 5%, which verifies the effectiveness and accuracy of this method.

To solve the problems of poor real-time tension tracking, large overshoot, long adjustment time, and large tension fluctuation error that exist in the current control system for yarn feeding in the circular weft knitting machine, this paper presents an optimized and improved adaptive genetic algorithm (AGA) for adjusting the PID (Proportional Integral Derivative) parameters of the tension control part of the yarn-conveying system (AGA-PID). The algorithm is combined with the field-oriented control technology of the permanent magnet synchronous motor to design a closed-loop control strategy for the yarn-conveying system of a circular weft knitting machine. The MATLAB-Simulink simulation model was used to analyze the external tension loop-based AGA-PID controller and permanent magnet synchronous motor dual closed-loop control strategy of the yarn transport control system. The experimental verification was conducted by constructing an experimental platform that simulates the real process of yarn transportation. The outcomes of system simulations and experiments have consistently demonstrated that the AGA-PID control algorithm outperforms the GA-PID and PID control algorithms in terms of overshooting, response speed, stability, and anti-jamming ability. The yarn transport control system, which is designed to operate based on an AGA-PID control algorithm, is capable of reducing the fluctuations in tension that occur during the transportation of yarn and exhibits enhanced control accuracy, effectively stabilizing yarn tension control during the conveying process. The application of this algorithm can enhance the overall elasticity uniformity and surface flatness of knitted fabrics, thereby facilitating the realization of adjustable and controllable local elasticity in fabrics.

This article focuses on the nonlinear dynamics of transverse vibration of the axially moving yarn system. In this article, the motion of yarn in actual production is analyzed, and the transverse nonlinear vibration equation of the viscoelastic axially moving yarn system with Kelvin model is established by using Newton’s second law. In the modeling process, the viscoelasticity of yarn material and the periodic fluctuation of tension in the process of movement are considered. The partial differential control equations of the system are transformed into ordinary differential equations by the Galerkin method. In the first three modes, when the speed is low, the related trial functions occupy the main part, and with the increase of speed, the trial functions of other orders occupy more proportion in the modal functions. Through numerical analysis, it is found that when the moving yarn is subjected to external excitation, the lateral vibration displacement has an increasing trend, and it is found that the nonlinear dynamic phenomenon alternates with the change of system parameters, such as single periodic motion, double periodic motion, and multiple periodic motion. Finally, an experimental platform for lateral vibration of yarn transmission was built and its working principle introduced. The lateral vibration of axially moving yarn was studied from the experimental point of view. It was proved that there are abundant phenomena of periodic motion, period doubling motion, and chaotic motion in the axially moving yarn system, which provides an experimental reference for theoretical research of lateral nonlinear vibration of axially moving yarn.

This paper investigates the mechanical properties of a blended yarn and its correlation with the characteristics of constituent yarns of different materials. Each yarn’s creep and stress relaxation tests are curves fitted to a six-element constitutive model. The results show that the higher the chemical fiber content in the yarn, the better the plastic properties. The experimental data fit the six-element model with 99% confidence. Compared with the commonly used viscoelastic Burgers and Ering models, the six-element model has a much more precise forecasting ability. Within the scope of this study, the ratio of yield stress to initial stress under different stress conditions calculated from the same yarn test is similar, and the ratio is only related to the blending ratio of polyester-cotton blended yarn. In yarns with strong plasticity, this ratio can reflect the proportional relationship between plastic deformation and elastic deformation in relaxation experiments.

In order to improve the automatic production efficiency of the textile workshop and reduce the labor cost and error rate, this study designed a multi label recognition model YoloColor-Net based on deep learning, which aims to realize the automatic detection and recognition of the bobbin shape and yarn color on the yarn frame in the textile workshop. Firstly, according to the research needs, a dataset sample containing 12,173 textile bobbin images was collected and constructed independently. Then, the traditional yolov5 model is improved by designing the convolution network of yarn color recognition, which solves the problem of missing detection of the bobbin when detecting the bobbin shape and yarn color at the same time. Secondly, the lightweight DSConv module is used to replace the ordinary convolution of the Backbone layer to reduce the parameters of YoloColor-Net and improve the running speed. Finally, the improved attention mechanism (ICBAM) is added to the Backbone and Neck layers of YoloColor-Net to improve the accuracy of bobbin recognition. The experimental results show that the detection accuracy of the improved YoloColor-Net model is 99.3%, the number of model parameters is reduced by 10.4%, and the GFLOPS is reduced by 17.1%. FPS increased from 43.13 to 67.23, an increase of 55.9%. Therefore, the proposed model can basically meet the task of bobbin automatic detection and recognition, and consider the initial localization deployment.

Aiming at the problems of low production efficiency and high manual dependence in the heat-sealing process of the pillow packaging machine, the existing optimization methods of process parameters were improved, and an intelligent decision-making model of the longitudinal sealing heat-sealing process based on the radial basis function neural network and orthogonal least square method was proposed to realize the efficient and accurate optimization of heat-sealing process parameters. By analyzing the fracture yield strength of the composite, the target heat-sealing strength range was determined. The heat-sealing temperature, heat-sealing speed, and heat-sealing plate distance were selected as key process variables, and the actual production data were used to train the model to accurately construct the nonlinear mapping relationship between heat-sealing process parameters and heat-sealing strength. On this basis, the genetic algorithm optimization framework with the model predictive output as the fitness function is designed to realize the rapid search of the optimal combination of process parameters. The optimization results were introduced into the pillow packaging machine for a verification test. The measured heat-sealing strength was stable within the target range. The maximum error of the optimization group was less than 10%, and the average error was less than 5%, which was significantly better than the effect of manual experience. The experimental results show that the proposed method can effectively improve the efficiency and consistency of process optimization under the premise of ensuring the quality of heat-sealing, meet the requirements of automatic production for high precision and low consumption of the heat-sealing process optimization, and realize the comprehensive improvement of efficiency, accuracy, and intelligent level in the longitudinal heat-sealing process of the pillow packaging machine.