Chen Hao, Zhang Haifei, Yang Yuwei, Zhang Qiong
School of Information Engineering, Nantong Institute of Technology, Nantong 226002, China.
ACS Omega. 2024 Aug 1;9(32):34725-34734. doi: 10.1021/acsomega.4c03747. eCollection 2024 Aug 13.
In chemical production processes, outliers are inevitable. Many existing feature extraction algorithms are overly sensitive to outliers and excessively focus on secondary features while ignoring the key features in the data. To address this problem, the Frobenius norm based soft linear discriminant analysis algorithm (FBSLA) is proposed in this paper. Specifically, FBSLA uses the Frobenius norm instead of its square as a metric to enhance the robustness of the algorithm. Furthermore, a nonreduced dimensionality projection matrix is introduced to make the training data features more obvious. Additionally, soft constraint is adopted instead of the traditional hard constraint to reduce the sensitivity caused by outliers. To validate the effectiveness of FBSLA, in this paper, experiments are conducted on the Tennessee Eastman Process and the Penicillin Fermentation Process data sets. According to experimental results, FBSLA significantly outperforms other state-of-the-art algorithms in terms of fault detection accuracy.
在化学生产过程中，异常值是不可避免的。许多现有的特征提取算法对异常值过于敏感，过度关注次要特征而忽略了数据中的关键特征。为了解决这个问题，本文提出了基于Frobenius范数的软线性判别分析算法（FBSLA）。具体来说，FBSLA使用Frobenius范数而非其平方作为度量标准，以增强算法的鲁棒性。此外，引入了一个不降维的投影矩阵，使训练数据特征更加明显。另外，采用软约束而非传统的硬约束来降低由异常值引起的敏感性。为了验证FBSLA的有效性，本文对田纳西伊士曼过程和青霉素发酵过程数据集进行了实验。根据实验结果，FBSLA在故障检测准确率方面显著优于其他现有最先进的算法。
