棉纱条干均匀度预测数据

在纺织生产中，棉纱质量不可忽视。优质的棉纱对织物的生产效率、品质和市场竞争力都有重要影响。在衡量棉纱质量时，棉纱条干均匀度是一个关键指标，而原棉性能（如上半部长度、整齐度等）是影响棉纱条干均匀度的重要因素。由于原棉性能与棉纱条干均匀度之间呈现出复杂的非线性关系，使得棉纱条干均匀度难以准确预测。为解决棉纱条干均匀度难以预测的问题，提出了一种改进麻雀搜索算法（ISSA）优化BP神经网络的预测方法，对棉纱条干均匀度进行预测，能得到较好预测结果，从而为本行业的所有企业制定生产策略，更好地为用户提供个性化的商品和服务。1数据采集：将棉纱成形过程中采集到的9个原棉指标进行特征提取，作为BP神经网络预测模型的输入变量。2数据处理：使用单隐层BP神经网络结构（三层结构），输入层有9个神经元对应9个特征指标，输出层有1个神经元对应棉纱条干均匀度的预测值。利用改进麻雀搜索算法（ISSA）对BP神经网络的初始权值和阈值进行优化，以提高预测模型的性能，建立ISSA‐BP神经网络模型。为验证改进算法的有效性，利用Python进行训练和仿真，并与BP模型、GA‐BP模型、PSO‐BP模型和SSA‐BP模型进行预测结果对比。3数据运用：结果表明：ISSA‐BP模型在棉纱条干均匀度预测中平均相对误差为1.52%，预测性能较优，误差较小，预测结果较为理想，可以有效预测棉纱条干均匀度。

In textile production, the quality of cotton yarn cannot be overlooked. High-quality cotton yarn has a significant impact on the production efficiency, quality and market competitiveness of fabrics. When evaluating cotton yarn quality, yarn evenness is a key indicator, while raw cotton properties (such as upper half mean length, uniformity ratio, etc.) are important factors affecting cotton yarn evenness. Due to the complex nonlinear relationship between raw cotton properties and cotton yarn evenness, it is difficult to accurately predict cotton yarn evenness. To address the challenge of predicting cotton yarn evenness accurately, a prediction method based on Back Propagation (BP) neural network optimized by Improved Sparrow Search Algorithm (ISSA) is proposed, which can achieve good prediction results for cotton yarn evenness, thereby helping enterprises in the industry formulate production strategies and better provide personalized products and services to users.
1. Data Collection: Extract features from 9 raw cotton indicators collected during the cotton yarn forming process, which serve as input variables for the BP neural network prediction model.
2. Data Processing: Adopt a single-hidden-layer BP neural network structure (three-layer structure), where the input layer has 9 neurons corresponding to the 9 feature indicators, and the output layer has 1 neuron corresponding to the predicted value of cotton yarn evenness. The Improved Sparrow Search Algorithm (ISSA) is used to optimize the initial weights and thresholds of the BP neural network to improve the performance of the prediction model, thus establishing the ISSA-BP neural network model. To verify the effectiveness of the improved algorithm, Python is used for training and simulation, and the prediction results are compared with those of the BP model, GA-BP model, PSO-BP model and SSA-BP model.
3. Data Application: The results show that the ISSA-BP model has an average relative error of 1.52% in cotton yarn evenness prediction, with better prediction performance, smaller errors and ideal prediction results, which can effectively predict cotton yarn evenness.