Parvez Mohammad Anwar, Mehedi Ibrahim M
Department of Chemical Engineering, College of Engineering, King Faisal University, Al-Ahsa 31982, Saudi Arabia.
School of Robotics, XJTLU Entrepreneur College (Taicang), Xi'an Jiaotong-Liverpool University, No. 111 Taicang Ave., Suzhou 215400, China.
Polymers (Basel). 2025 Aug 31;17(17):2382. doi: 10.3390/polym17172382.
The polymer industry gained increasing importance due to the ability of polymers to replace traditional materials such as wood, glass, and metals in various applications, offering advantages such as high strength-to-weight ratio, corrosion resistance, and ease of fabrication. Among key performance indicators, melt flow rate (MFR) plays a crucial role in determining polymer quality and processability. However, conventional offline laboratory methods for measuring MFR are time-consuming and unsuitable for real-time quality control in industrial settings. To address this challenge, the study proposes a leveraging artificial intelligence with machine learning-based melt flow rate prediction for polymer properties analysis (LAIML-MFRPPPA) model. A dataset of 1044 polymer samples was used, incorporating six input features such as reactor temperature, pressure, hydrogen-to-propylene ratio, and catalyst feed rate, with MFR as the target variable. The input features were normalized using min-max scaling. Two ensemble models-kernel extreme learning machine (KELM) and random vector functional link (RVFL)-were developed and optimized using the pelican optimization algorithm (POA) for improved predictive accuracy. The proposed method outperformed traditional and deep learning models, achieving an R of 0.965, MAE of 0.09, RMSE of 0.12, and MAPE of 3.4%. A SHAP-based sensitivity analysis was conducted to interpret the influence of input features, confirming the dominance of melt temperature and molecular weight. Overall, the LAIML-MFRPPPA model offers a robust, accurate, and deployable solution for real-time polymer quality monitoring in manufacturing environments.
由于聚合物能够在各种应用中替代木材、玻璃和金属等传统材料，并具有诸如高强度重量比、耐腐蚀性和易于加工等优点，聚合物行业变得越来越重要。在关键性能指标中，熔体流动速率（MFR）在确定聚合物质量和可加工性方面起着至关重要的作用。然而，传统的离线实验室测量MFR的方法耗时且不适用于工业环境中的实时质量控制。为应对这一挑战，该研究提出了一种基于人工智能和机器学习的熔体流动速率预测用于聚合物性能分析（LAIML-MFRPPPA）模型。使用了一个包含1044个聚合物样品的数据集，纳入了诸如反应器温度、压力、氢丙烯比和催化剂进料速率等六个输入特征，并将MFR作为目标变量。使用最小-最大缩放对输入特征进行了归一化处理。开发并使用鹈鹕优化算法（POA）优化了两种集成模型——核极限学习机（KELM）和随机向量函数链接（RVFL），以提高预测准确性。所提出的方法优于传统模型和深度学习模型，实现了0.965的R值、0.09的平均绝对误差（MAE）、0.12的均方根误差（RMSE）和3.4%的平均绝对百分比误差（MAPE）。进行了基于SHAP的敏感性分析以解释输入特征的影响，证实了熔体温度和分子量的主导作用。总体而言，LAIML-MFRPPPA模型为制造环境中的聚合物实时质量监测提供了一种强大、准确且可部署的解决方案。
