多模态过程中新模态过程建模方法

多模态过程中新出现的模态过程短期内无法获得充足的建模数据,且传统统计控制方法无法有效地估计过程特性.鉴于此,提出一种基于历史模型数据相关特性建立初步模型的方法,充分利用已有多模态历史数据的相关特性,从历史数据中寻找与当前数据特征相似的数据进行补充,建立初始模型,并利用新积累的数据迭代初步模型,逐步实现准确描述过程特性的算法.通过在田纳西-伊斯曼过程中的大量仿真,表明了所提出方法的可行性和有效性.     

多模态过程的全自动离线模态识别方法

多模态是复杂工业生产过程的普遍特性.不同模态具有不同的过程特性,需要建立不同的模型,因此离线建模数据的模态划分与识别是整个多模态过程建模的关键问题之一.目前,常用的聚类算法需要对其结果进行人工分析和后续处理,无法真正实现多模态过程的全自动模态识别.因此,本文提出一种全自动的多模态过程离线模态识别方法.首先通过宽度为H的大切割窗口对数据进行切割,利用改进的K-means聚类算法对窗口单元进行聚类;根据聚类结果,对稳定模态淹没现象进行处理,得到模态的初步划分结果;最终,利用小滑动窗口L,对稳定模态及过渡模态交接区域进行细划分,准确定位稳定模态与过渡模态的分割点.算法实现了多模态过程的全自动离线识别,并给出合理有效的识别结果.仿真分析表明此方法能够实现模态的自动识别,且识别结果准确.     

基于差分分段PCA的多模态过程故障监测

多模态的故障监测是一个复杂的问题, 既需要考虑稳定模态下的故障监测, 也需要考虑不同模态间的过渡故障监测. 不同稳定模态下的数据具有不同的相关关系, 对每个稳定模态需要建立不同的稳定模态模型. 当稳定生产模态发生改变时, 生产过程进入过渡模态, 需要考虑过渡变量相关关系的变化. 本文通过对过渡数据差分, 得到变量相对变化信息. 利用主成分分析(Principal component analysis, PCA)分段对差分变量的相关特性进行分析, 提取相对变化的特征. 最后以实际连续退火机组生产线为背景, 用基于差分分段PCA的多模态方法对多模态过程进行故障监测, 发现算法很好地反映了实际过渡过程机理, 验证了算法的有效性.     

基于概率密度PCA的多模态过程故障检测

为了提高故障检测和分类能力,提出基于概率密度PCA的多模态过程故障检测算法。对各模态的训练数据建立PCA模型,计算各个模型的控制限和匹配系数。根据匹配系数计算各模态统一的控制限。对新来的数据,运用概率密度确定其模态。新来数据向对应模态的模型上投影并计算统一的统计量,比较统计量与控制限进行多模态过程故障检测。把该方法应用到数值例子和半导体过程中,仿真结果表明,该算法在分类及多模态过程故障检测方面具有很高的准确性。     

跨媒体智能关联分析与语义理解理论与技术研究进展

深入分析了跨媒体智能关联分析与语义理解理论技术的最新研究进展,包括多模态数据的统一表达、知识引导的数据融合、跨媒体关联分析、基于知识图谱的跨媒体表征技术以及面向多模态的智能应用.其中,多模态数据的统一表达是对跨媒体信息进行分析推理的先决条件,利用多模态信息间的语义一致性剔除冗余信息,通过跨模态相互转化来实现跨媒体信息统一表达,学习更全面的特征表示;跨媒体关联分析立足于图像语言、视频语言以及音视频语言的跨模态关联分析与理解技术,旨在弥合视觉、听觉以及语言之间的语义鸿沟,充分建立不同模态间的语义关联;基于知识图谱的跨媒体表征技术通过引入跨媒体的知识图谱,从跨媒体知识图谱构建、跨媒体知识图谱嵌入以及跨媒体知识推理3个方面展开研究,增强跨媒体数据表征的可靠性,并提升后续推理任务的分析效率和准确性;随着跨模态分析技术的快速发展,面向多模态的智能应用得到了更多的技术支撑,依据智能应用所需要的领域知识,选取了多模态视觉问答,多模式视频摘要、多模式视觉模式挖掘、多模式推荐、跨模态智能推理和跨模态医学图像预测等跨模态应用实例,梳理了其在多模态数据融合以及跨媒体分析推理方面的研究进展.     

多模态深度学习综述

在多模态深度学习发展前期总结当前多模态深度学习,发现在不同多模态组合和学习目标下,多模态深度学习实现过程中的共有问题,并对共有问题进行分类,叙述解决各类问题的方法。具体来说,从涉及自然语言、视觉、听觉的多模态学习中考虑了语言翻译、事件探测、信息描述、情绪识别、声音识别和合成以及多媒体检索等方面研究,将多模态深度学习实现过程中的共有问题分为模态表示、模态传译、模态融合和模态对齐四类,并对各类问题进行子分类和论述,同时列举了为解决各类问题产生的神经网络模型。最后论述了实际多模态系统、多模态深度学习研究中常用的数据集和评判标准,并展望了多模态深度学习的发展趋势。     

多模态数据融合综述

随着当今信息技术的飞速发展,信息的存在形式多种多样,来源也十分广泛。不同的存在形式或信息来源均可被称之为一种模态,由两种或两种以上模态组成的数据称之为多模态数据。多模态数据融合负责将多个模态的信息进行有效的整合,汲取不同模态的优点,完成对信息的整合。自然现象具有十分丰富的特征,单一模态很难提供某个现象的完整信息。面对保持融合后具有各个模态信息的多样性以及完整性、使各个模态的优点最大化、减少融合过程造成的信息损失等方面的融合要求,如何对各个模态的信息进行融合成为了多个领域广泛存在的一个新挑战。简要阐述了常见的多模态融合方法、融合架构,总结了三个常见的融合模型,简要分析协同、联合、编解码器三大架构的优缺点以及多核学习、图像模型等具体融合方法。在多模态的应用方面,对多模态视频片段检索、综合多模态信息生成内容摘要、多模态情感分析、多模态人机对话系统进行了分析与总结。指出了当前多模态融合出现的问题,并提出未来的研究方向。     

局部近邻标准化偏最小二乘的多模态间歇过程故障检测

本文针对多模态间歇过程数据多中心和模态方差差异明显的问题,提出了一种基于局部近邻标准化偏最小二乘方法.首先,采用统计模量方法处理间歇过程数据,再利用局部近邻标准化方法将统计模量后的训练数据进行高斯化处理,建立偏最小二乘监控模型,确定控制限;然后,同样对统计模量后的测试数据进行局部近邻标准化处理,再计算测试数据的高斯偏最小二乘监控指标,进行过程监视及故障检测.最后,通过数值实例和青霉素发酵过程验证方法有效性.实验结果表明所提方法解决了故障样本近邻集跨模态问题,对多模态数据具有更好的故障检测能力.     

基于话语间时序多模态数据的情绪分析方法

长期以来, 传统的基于单模态数据情绪分析方法存在分析角度单一、分类准确率低下等问题, 时序多模态数据的分析方法为解决这些问题提供了可能. 本文基于话语间的时序多模态数据, 对现有的多模态情绪分析方法进行了改进, 使用双向门控循环网络(Bi-GRU)结合模态内和跨模态的上下文注意力机制进行情绪分析, 最后在MOSI和MOSEI数据集上进行验证. 实验表明, 利用话语间的时序多模态数据, 并且充分融合模态内以及跨模态上下文信息的方法, 能够从多模态特征和时序特征的角度进行情绪分析, 从而有效提高情绪分析任务的分类准确率.     

基于差分的动态加权SVDD在多模态过程故障检测中的应用

传统SVDD作为一种单模态静态故障检测算法,对多模态动态过程故障的检测难以保证其检测的准确性和实时性。为了解决这一问题,提出一种基于近邻差分加权动态SVDD检测方法（NND-DWSVDD）。首先利用NND剔除数据多模态结构,保证过程数据服从单峰分布;对差分处理后的数据引入动态方法并加入权值将有用的信息凸显出来;最后利用SVDD方法建立监测模型实现在线监测。NND-DWSVDD提高了多模态动态过程故障检测率,对于多模态动态过程故障检测,NND-DWSVDD不要求多模型建模,只需单独的一个模型,符合单模态故障检测要求。通过多模态数值例子和半导体生产过程数据对该方法的有效性进行了验证。     

Modeling and monitoring of nonlinear multi-mode processes

In this paper, a new subspace separation method is proposed and a new modeling and monitoring approach in multi-mode processes based on subspace separation is proposed. The existing modeling methods have the following disadvantages: (1) different monitoring models are built in view of each different mode, which needs each mode to be able to offer fully complete modeling reference data. (2) The connection between each mode is ignored, which could be useful in process modeling and monitoring. The proposed method has the following advantages: (1) the common subspace is extracted and the monitoring performance of multi-mode processes is significantly improved. (2) New subspace separation is used to establish an integrated monitoring system, which would simplify the monitoring model structure and enhance its reliability. (3) The direct relationship of input dataset and output dataset is considered in the multi-mode processes, which is crucial for the complex industry process. Experiment results show effectiveness of the proposed method.     

An adaptive multimode process monitoring strategy based on mode clustering and mode unfolding

A comprehensive monitoring framework is proposed for multimode processes in which mode clustering and mode unfolding are integrated within an adaptive strategy. To start, an aggregated k-means algorithm produces an optimal ensemble clustering solution for a multimode process dataset. Next, a mode unfolding (MU) scheme enables the development of a single principal component analysis (PCA) model for processes operating under multiple desired steady-states (modes). Finally, adaptive strategies for online mode identification and model updating are presented to address the challenges in fault detection in the presence of multiple operating modes. The validity and usefulness of the adaptive MU-PCA based monitoring framework is demonstrated through a study of the Tennessee Eastman benchmark process.     

Phase analysis and statistical modeling with limited batches for multimode and multiphase process monitoring

For multimode batch processes, the conventional modeling methods in general require that sufficient batches should be available for every mode, which, however, cannot be guaranteed in practice. It may be impractical to conduct enough trial runs and wait until sufficient batches are available before development of monitoring models for each mode. Starting from limited batches, how to derive reliable process information and develop monitoring models has been an important question for successful online multimode batch process monitoring. To address this problem, this article proposes a phase analysis and statistical modeling strategy with limited batches. One mode which has obtained sufficient batches is chosen as the reference mode while the other modes which can only get limited batches work as alternative modes. Starting from limited batches, the proposed algorithm addresses two issues, concurrent phase partition and analysis of between-mode relative changes. First, for each alternative mode, generalized time-slices are constructed by combining several consecutive time-slices within a short time region to explore local process correlations. The time-varying characteristics are then concurrently analyzed across modes so that multiple sequential phases are identified simultaneously for all modes. Then phase-representative data units are arranged by variable-unfolding the conventional time-slices for the reference mode and the generalized time-slices for each alternative mode respectively. Between-mode statistical analysis is performed within each phase where the relative changes from the reference mode to each alternative mode are analyzed. From the between-mode perspective, different types of relative variations in each alternative mode are separated and modeled for online monitoring. Starting from limited batches, online batch process monitoring can be conducted, providing reliable fault detection performance. The proposed algorithm is illustrated with a typical multiphase batch process with multiple modes.     

基于稀疏残差距离的多工况过程故障检测方法研究

针对多工况过程,本文提出一种新的基于稀疏残差距离（Sparse residual distance,SRD）统计指标的故障检测方法.首先对正常的多工况标准化后数据直接进行稀疏分解,提取多个工况数据间相关关系,得到字典和对应的稀疏编码,以便构建全局检测模型,避免分工况且突出数据特征.然后计算正常多工况数据的近似值,构建稀疏残差空间,提出计算稀疏残差k近邻距离构建故障检测统计量,利用k近邻捕捉过程具有的非线性、多工况特征.最后通过数值案例和TE（Tennessee Eastman）生产过程进行仿真实验,验证了所提方法的有效性.     

一种基于多工况识别的过程在线监测方法

在包含多个工况的工业生产过程中,各个稳态工况之间存在着一定的过渡过程,虽然过渡时间较短,但其复杂的动态特性使得传统的过程监测方法难以获得满意的效果,为此提出一种基于多工况识别的过程监测方法.首先,通过窗口切割对基本稳态工况进行识别;然后,采用滑动窗技术确定过渡过程的起始和结束时间,并进一步基于差分分段技术对过渡过程的子阶段进行分类,考虑到各阶段数据的不同分布特性,利用独立成分分析和主元分析分别提取各阶段数据的非高斯和高斯信息;最后根据贝叶斯推断将3个统计量进行重构, 实现多工况过程的在线监测.通过TE过程的仿真研究,验证了所提出方法的可行性和有效性.     

Energy consumption mode identification and monitoring method of process industry system under unstable working conditions

Process industry systems under unstable working conditions are prone to potential anomalies, deviating from the original transition trajectory, and taking longer than expected to return to stability due to persistent disturbances from uncertainties and experience-based regulation errors. The energy waste caused by this situation has not received sufficient attention, and cannot be addressed by existing energy consumption monitoring methods. Herein, an energy consumption mode (ECM) identification and monitoring method under unstable working conditions is proposed, consisting of ECM identification model and multi-mode dynamic monitoring model, focusing on the variation rules of the correlation between energy consumption and other states of the system. In the ECM identification stage, the ECM correlation parameters that reflect the comprehensive production information are selected. Then, given the transfer characteristics of ECM, a Hidden Semi-Markov Model (HSMM) is constructed to fit the migration between modes and the duration within modes. The Variational Bayesian Gaussian Mixture Model is introduced to improve the HSMM, which solves the problem of lacking prior knowledge of ECM and achieves the automatic classification and online identification of ECM. In the dynamic monitoring stage of multi-ECMs, a series of dynamic kernel principle component analysis models are established, and the corresponding monitoring thresholds are set for each ECM. By calculating the maximum of the posteriori probability and the mode thresholds, the ECMs under unstable conditions can be accurately identified and automatically monitored. Compared with previous methods, the proposed method reduces the false detection rate and missed detection rate of abnormal ECM identification to 1.04% and 1.31% in the actual slag grinding production process, which proves its effectiveness.     

基于时延SDG和ICA的多工况过程故障预测方法

针对多工况生产过程,提出基于时延符号有向图(SDG)和独立成分分析(ICA)的在线故障预测方法.时延符号有向图描述了过程变量间信息传递的方向和时延大小;在有向图模型基础上,对过程数据进行信息同步校正;ICA方法应用于校正后的过程数据,使得基于ICA的性能监测方法具有良好的故障预测能力.在空分设备中的应用结果表明,该方法...