Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification...Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.展开更多
由于水质数据特征复杂、关联度参差不齐而导致溶解氧浓度预测难度较大,为提高水质溶解氧浓度预测的准确性,提出了一种基于特征工程和北方苍鹰优化算法的长短期记忆网络(Feature Engineering-Northern Goshawk Optimization-Long Short T...由于水质数据特征复杂、关联度参差不齐而导致溶解氧浓度预测难度较大,为提高水质溶解氧浓度预测的准确性,提出了一种基于特征工程和北方苍鹰优化算法的长短期记忆网络(Feature Engineering-Northern Goshawk Optimization-Long Short Term Memory,FE-NGO-LSTM)混合模型。首先对水质数据集进行缺失值补齐、特征筛选与特征多项式构造,然后基于NGO-LSTM模型优化模型参数,提升预测性能;对不同多项式阶数下的特征预测效果进行分析之后,将该模型与基于灰狼优化算法、鲸鱼优化算法及粒子群优化算法的LSTM模型进行对比;最后,在太湖流域东苕溪城南监测断面对该模型进行了验证,计算FE-NGO-LSTM模型预见期为4,8,12,16,20,24 h的预测结果。试验结果显示:当多项式阶数为2阶时,模型预测效果最好,FE-NGO-LSTM模型相比基于其他优化算法的LSTM模型,平均绝对误差、均方误差、均方根误差分别至少降低9.0%,12.9%及6.3%,且随着预见期的增加,预测误差仍在可接受范围内,说明FE-NGO-LSTM模型在预测溶解氧浓度时具有一定优势与泛化性。展开更多
电能质量扰动识别方法通常是先通过数字信号处理工具对信号进行检测和特征提取,再采用人工智能方法对特征进行分类识别,增加了识别过程的复杂性和冗余性。提出一种基于判别字典学习(DDL)的稀疏表示电能质量扰动识别方法,可有效减少识别...电能质量扰动识别方法通常是先通过数字信号处理工具对信号进行检测和特征提取,再采用人工智能方法对特征进行分类识别,增加了识别过程的复杂性和冗余性。提出一种基于判别字典学习(DDL)的稀疏表示电能质量扰动识别方法,可有效减少识别步骤、降低复杂性,并提高识别率。该方法首先采用主成分分析方法将K类扰动训练样本集降维为扰动降维特征训练样本集,由各类样本分别训练出冗余子字典,然后级联成判别字典。接着基于l0范数算法求解出降维测试信号在该判别字典下的稀疏表示矩阵,最后利用不同的冗余子字典重构测试样本,由冗余残差最小值确定目标归属类,实现对电能质量扰动信号的识别。仿真实验结果表明该方法能有效地对不同电能质量扰动进行识别,过程简单、数据量少、抗噪声鲁棒性好,在信噪比20 d B以上的噪声环境中电能质量扰动识别准确率达到95%以上。展开更多
文摘Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.
文摘由于水质数据特征复杂、关联度参差不齐而导致溶解氧浓度预测难度较大,为提高水质溶解氧浓度预测的准确性,提出了一种基于特征工程和北方苍鹰优化算法的长短期记忆网络(Feature Engineering-Northern Goshawk Optimization-Long Short Term Memory,FE-NGO-LSTM)混合模型。首先对水质数据集进行缺失值补齐、特征筛选与特征多项式构造,然后基于NGO-LSTM模型优化模型参数,提升预测性能;对不同多项式阶数下的特征预测效果进行分析之后,将该模型与基于灰狼优化算法、鲸鱼优化算法及粒子群优化算法的LSTM模型进行对比;最后,在太湖流域东苕溪城南监测断面对该模型进行了验证,计算FE-NGO-LSTM模型预见期为4,8,12,16,20,24 h的预测结果。试验结果显示:当多项式阶数为2阶时,模型预测效果最好,FE-NGO-LSTM模型相比基于其他优化算法的LSTM模型,平均绝对误差、均方误差、均方根误差分别至少降低9.0%,12.9%及6.3%,且随着预见期的增加,预测误差仍在可接受范围内,说明FE-NGO-LSTM模型在预测溶解氧浓度时具有一定优势与泛化性。
文摘电能质量扰动识别方法通常是先通过数字信号处理工具对信号进行检测和特征提取,再采用人工智能方法对特征进行分类识别,增加了识别过程的复杂性和冗余性。提出一种基于判别字典学习(DDL)的稀疏表示电能质量扰动识别方法,可有效减少识别步骤、降低复杂性,并提高识别率。该方法首先采用主成分分析方法将K类扰动训练样本集降维为扰动降维特征训练样本集,由各类样本分别训练出冗余子字典,然后级联成判别字典。接着基于l0范数算法求解出降维测试信号在该判别字典下的稀疏表示矩阵,最后利用不同的冗余子字典重构测试样本,由冗余残差最小值确定目标归属类,实现对电能质量扰动信号的识别。仿真实验结果表明该方法能有效地对不同电能质量扰动进行识别,过程简单、数据量少、抗噪声鲁棒性好,在信噪比20 d B以上的噪声环境中电能质量扰动识别准确率达到95%以上。
