The application of artificial neural network (ANN) models to achieve higher accuracy in industrial sensing has become a popular research topic in recent years. However, neural network models are purely data-driven mul...The application of artificial neural network (ANN) models to achieve higher accuracy in industrial sensing has become a popular research topic in recent years. However, neural network models are purely data-driven multivariate “black-box” models, and the features extracted from the hidden layer have no actual physical meaning, making the performance of ANN-based sensing models unstable and difficult to practically apply at process industry sites. To address these challenges, this paper proposes a generalized ANN model called the partial least squares (PLS)-assisted optimization network (PLSaoNET). PLSaoNET employs the PLS model to assist in determining the initialization weights of the network and the number of hidden-layer neurons. The subsequent training serves as a reoptimization process guided by the PLS regression result, enabling the network to incorporate statistical constraints and thereby reducing its reliance on data. In addition, to address the problem of uneven distributions of sample labels at industrial sites, this paper designs a stratified sampling method for network retraining. The efficiency and superiority of the proposed method are verified via two industrial sensing applications: the monitoring of iron grade in iron ore concentrate slurry samples based on laser-induced breakdown spectroscopy (LIBS) data, and the assessment of the quality of diesel fuels based on near-infrared (NIR) spectroscopy data. In comparison with a PLS regression model and a Xavier initialization-based backpropagation neural network (BPNN) model, PLSaoNET exhibits the best modeling accuracy and generalization performance. This work designs a complete theoretical framework to guide the determination of hyperparameters and specify the solution paths of the network, thereby satisfying the triple requirements of accuracy, robustness, and ease of use in industrial processes. The proposed model holds great potential for improving the accuracy and reliability of industrial sensing in production processes.展开更多
Unanticipated wear of tunnel boring machine(TBM)disc cutters is a critical factor causing project delays and cost overruns in tunneling engineering.Accurate,real-time prediction of the cutter’s wear state is therefor...Unanticipated wear of tunnel boring machine(TBM)disc cutters is a critical factor causing project delays and cost overruns in tunneling engineering.Accurate,real-time prediction of the cutter’s wear state is therefore essential for enabling predictive maintenance.Data-driven methods,particularly deep learning,have shown promise for this task,but their performance is constrained by the scarcity of high-quality labeled data in practical industrial settings.To address this challenge,we propose a novel,decoupled semi-supervised framework called PL-HLANet.The first component of this framework is a multi-view pseudolabeling(PL)module,which mines high-confidence supervisory signals from massive unlabeled data by leveraging heterogeneous views derived from feature engineering and diverse model architectures;it is followed by a consistency check to ensure label quality.This process effectively augments the training set while correcting for sampling bias.Subsequently,a specialized hierarchical hybrid attention network(HLANet)is used to make predictions.The HLANet organically integrates a temporal convolutional network(TCN)for local feature extraction,a bidirectional long short-term memory(Bi-LSTM)network for capturing temporal dynamics,and a custom attention mechanism for focusing on critical information.Experiments on a realworld tunneling dataset show that PL-HLANet significantly outperforms both supervised and mainstream semi-supervised baselines,such as the Mean Teacher and FixMatch.The framework’s effectiveness is further substantiated by validations of its architectural design and data-driven selection of hyperparameters.Moreover,PL-HLANet has a high inference speed,showcasing its practicality for real-world scenarios.Our work provides an effective solution for machining equipment monitoring in datascarce industrial environments.展开更多
为探究不同贮藏温度对枇杷采后品质的影响,以红肉枇杷“大五星”为材料,设置0℃、8℃及程序降温(Low Temperature Conditioning,LTC)3种低温处理,贮藏35 d,测定果实硬度、褐变指数,采用HS-SPME-GC-MS(Head Space Solid-Phase Microextra...为探究不同贮藏温度对枇杷采后品质的影响,以红肉枇杷“大五星”为材料,设置0℃、8℃及程序降温(Low Temperature Conditioning,LTC)3种低温处理,贮藏35 d,测定果实硬度、褐变指数,采用HS-SPME-GC-MS(Head Space Solid-Phase Microextraction and Gas Chromatography Mass Spectrometry)检测香气成分,结合PLS-DA(Partial Least Squares Discriminant Analysis)分析差异香气物质并综合评价品质。结果表明:21 d前3种处理果实硬度无显著差异,28 d、35 d时0℃处理硬度显著高于8℃和LTC处理,8℃和LTC处理间差异不显著;LTC处理在28 d、35 d时褐变指数显著低于0℃处理和8℃处理,0℃和8℃间无显著性差异。HS-SPME-GC-MS共检测到74种香气成分,本研究各贮藏期内共有的成分为27种,主要为醛类、酯类、萜烯类、酮类、芳香族类和其他类,其中含量最高的为醛类。醛类化合物中0 d时己醛含量最高,为48.25μg/kg,其次是壬醛和反-2-己烯醛,含量分别为23.25μg/kg和21.93μg/kg。酯类挥发性成分总含量次之,其中2-甲基丁酸甲酯是0 d时含量最高的酯类,为84.71μg/kg;随着贮藏时间的延长,各处理酯类总含量不断下降。PLS-DA统计结果显示,通过计算变量重要性投影数值得到不同贮藏方式下含量具有显著差异的7种香气物质,分别为:香叶基丙酮、α-蒎烯、对伞花烃、壬醛、辛醛、反-2-己烯醛和2-甲基丁酸甲酯。贮藏到35 d时,0℃处理果实的香叶基丙酮、α-蒎烯、对伞花烃和壬醛含量较高,LTC处理则产生较多的对伞花烃、壬醛、辛醛、反-2-己烯醛和2-甲基丁酸甲酯,8℃处理的果实仅2-甲基丁酸甲酯含量较高。结合贮藏期间枇杷的硬度、褐变指数及香气成分种类和含量变化,程序降温处理在延长贮藏时间后能更好地维持枇杷的采后品质,表现出较低的褐变程度和较优的香气保留效果。展开更多
为了快速识别市场中的劣质食用油,提出了一种结合激光诱导荧光(laser-induced fluorescence,LIF)技术与偏最小二乘判别分析(partial least squares-discriminant analysis,PLS-DA)的高品质食用油掺伪鉴别方法。首先利用实验室搭建的LIF...为了快速识别市场中的劣质食用油,提出了一种结合激光诱导荧光(laser-induced fluorescence,LIF)技术与偏最小二乘判别分析(partial least squares-discriminant analysis,PLS-DA)的高品质食用油掺伪鉴别方法。首先利用实验室搭建的LIF系统采集了橄榄油、芝麻油和花生油及其掺伪样本的荧光光谱数据;然后基于PLS-DA方法分别为橄榄油、芝麻油和花生油构建了掺伪鉴别模型;最后通过预测集对模型性能进行了评估。结果表明,PLS-DA模型能够准确捕捉掺伪样本与真实样本荧光光谱之间的差异性特征,在实验所得数据验证下,达到了100%的分类准确率。该方法可实现对掺伪食用油的高精度鉴别,为食品安全监管提供了科学的鉴别手段。展开更多
基金supported in part by the National Natural Science Foundation of China(62173321)in part by the Research Program of the Liaoning Liaohe Laboratory(LLL23ZZ-05-02)。
摘要The application of artificial neural network (ANN) models to achieve higher accuracy in industrial sensing has become a popular research topic in recent years. However, neural network models are purely data-driven multivariate “black-box” models, and the features extracted from the hidden layer have no actual physical meaning, making the performance of ANN-based sensing models unstable and difficult to practically apply at process industry sites. To address these challenges, this paper proposes a generalized ANN model called the partial least squares (PLS)-assisted optimization network (PLSaoNET). PLSaoNET employs the PLS model to assist in determining the initialization weights of the network and the number of hidden-layer neurons. The subsequent training serves as a reoptimization process guided by the PLS regression result, enabling the network to incorporate statistical constraints and thereby reducing its reliance on data. In addition, to address the problem of uneven distributions of sample labels at industrial sites, this paper designs a stratified sampling method for network retraining. The efficiency and superiority of the proposed method are verified via two industrial sensing applications: the monitoring of iron grade in iron ore concentrate slurry samples based on laser-induced breakdown spectroscopy (LIBS) data, and the assessment of the quality of diesel fuels based on near-infrared (NIR) spectroscopy data. In comparison with a PLS regression model and a Xavier initialization-based backpropagation neural network (BPNN) model, PLSaoNET exhibits the best modeling accuracy and generalization performance. This work designs a complete theoretical framework to guide the determination of hyperparameters and specify the solution paths of the network, thereby satisfying the triple requirements of accuracy, robustness, and ease of use in industrial processes. The proposed model holds great potential for improving the accuracy and reliability of industrial sensing in production processes.
基金supported by the National Natural Science Foundation of China(No.52305074)the National Key Research and Development Program of China(No.2021YFB3301603).
摘要Unanticipated wear of tunnel boring machine(TBM)disc cutters is a critical factor causing project delays and cost overruns in tunneling engineering.Accurate,real-time prediction of the cutter’s wear state is therefore essential for enabling predictive maintenance.Data-driven methods,particularly deep learning,have shown promise for this task,but their performance is constrained by the scarcity of high-quality labeled data in practical industrial settings.To address this challenge,we propose a novel,decoupled semi-supervised framework called PL-HLANet.The first component of this framework is a multi-view pseudolabeling(PL)module,which mines high-confidence supervisory signals from massive unlabeled data by leveraging heterogeneous views derived from feature engineering and diverse model architectures;it is followed by a consistency check to ensure label quality.This process effectively augments the training set while correcting for sampling bias.Subsequently,a specialized hierarchical hybrid attention network(HLANet)is used to make predictions.The HLANet organically integrates a temporal convolutional network(TCN)for local feature extraction,a bidirectional long short-term memory(Bi-LSTM)network for capturing temporal dynamics,and a custom attention mechanism for focusing on critical information.Experiments on a realworld tunneling dataset show that PL-HLANet significantly outperforms both supervised and mainstream semi-supervised baselines,such as the Mean Teacher and FixMatch.The framework’s effectiveness is further substantiated by validations of its architectural design and data-driven selection of hyperparameters.Moreover,PL-HLANet has a high inference speed,showcasing its practicality for real-world scenarios.Our work provides an effective solution for machining equipment monitoring in datascarce industrial environments.
摘要为探究不同贮藏温度对枇杷采后品质的影响,以红肉枇杷“大五星”为材料,设置0℃、8℃及程序降温(Low Temperature Conditioning,LTC)3种低温处理,贮藏35 d,测定果实硬度、褐变指数,采用HS-SPME-GC-MS(Head Space Solid-Phase Microextraction and Gas Chromatography Mass Spectrometry)检测香气成分,结合PLS-DA(Partial Least Squares Discriminant Analysis)分析差异香气物质并综合评价品质。结果表明:21 d前3种处理果实硬度无显著差异,28 d、35 d时0℃处理硬度显著高于8℃和LTC处理,8℃和LTC处理间差异不显著;LTC处理在28 d、35 d时褐变指数显著低于0℃处理和8℃处理,0℃和8℃间无显著性差异。HS-SPME-GC-MS共检测到74种香气成分,本研究各贮藏期内共有的成分为27种,主要为醛类、酯类、萜烯类、酮类、芳香族类和其他类,其中含量最高的为醛类。醛类化合物中0 d时己醛含量最高,为48.25μg/kg,其次是壬醛和反-2-己烯醛,含量分别为23.25μg/kg和21.93μg/kg。酯类挥发性成分总含量次之,其中2-甲基丁酸甲酯是0 d时含量最高的酯类,为84.71μg/kg;随着贮藏时间的延长,各处理酯类总含量不断下降。PLS-DA统计结果显示,通过计算变量重要性投影数值得到不同贮藏方式下含量具有显著差异的7种香气物质,分别为:香叶基丙酮、α-蒎烯、对伞花烃、壬醛、辛醛、反-2-己烯醛和2-甲基丁酸甲酯。贮藏到35 d时,0℃处理果实的香叶基丙酮、α-蒎烯、对伞花烃和壬醛含量较高,LTC处理则产生较多的对伞花烃、壬醛、辛醛、反-2-己烯醛和2-甲基丁酸甲酯,8℃处理的果实仅2-甲基丁酸甲酯含量较高。结合贮藏期间枇杷的硬度、褐变指数及香气成分种类和含量变化,程序降温处理在延长贮藏时间后能更好地维持枇杷的采后品质,表现出较低的褐变程度和较优的香气保留效果。
摘要为了快速识别市场中的劣质食用油,提出了一种结合激光诱导荧光(laser-induced fluorescence,LIF)技术与偏最小二乘判别分析(partial least squares-discriminant analysis,PLS-DA)的高品质食用油掺伪鉴别方法。首先利用实验室搭建的LIF系统采集了橄榄油、芝麻油和花生油及其掺伪样本的荧光光谱数据;然后基于PLS-DA方法分别为橄榄油、芝麻油和花生油构建了掺伪鉴别模型;最后通过预测集对模型性能进行了评估。结果表明,PLS-DA模型能够准确捕捉掺伪样本与真实样本荧光光谱之间的差异性特征,在实验所得数据验证下,达到了100%的分类准确率。该方法可实现对掺伪食用油的高精度鉴别,为食品安全监管提供了科学的鉴别手段。