基于深度残差网络的化工过程故障诊断

本工作提出了一种基于深度残差网络(DRN)的化工过程故障诊断方法，可从大量化工过程运行数据中自动提取故障特征。模型采用快捷连接缓解传统深度神经网络训练困难的问题，且使用批归一化(BN)方法，可有效缓解梯度消失/爆炸的问题。以田纳西?伊斯曼(TE)过程为实验对象对所提方法进行诊断性能评价实验，并与以往的基于传统深度学习模型的TE过程故障诊断方法进行对比，进一步探究了模型层数、BN技术和残差结构对故障诊断率的影响，最后，通过t分布随机邻域嵌入(t-SNE)方法对网络部分层的输出进行可视化。结果表明，模型对21种工况取得了94%的平均故障诊断率和0.30%的平均假阳率，表现出更加卓越的诊断性能。输出层的二维散点图显示了清晰的聚类，表明所提出的DRN模型能够对故障进行准确诊断。     

Knowledge-Based Virtual Modeling and Simulation of Manufacturing Processes for Industry 4.0

Abstract

Industry 4.0 aims at providing a digital representation of a production landscape, but the challenges in building, maintaining, optimizing, and evolving digital models in inter-organizational production chains have not been identified yet in a systematic manner. In this paper, various Industry 4.0 research and technical challenges are addressed, and their present scenario is discussed. Moreover, in this article, the novel concept of developing experience-based virtual models of engineering entities, process, and the factory is presented. These models of production units, processes, and procedures are accomplished by virtual engineering object (VEO), virtual engineering process (VEP), and virtual engineering factory (VEF), using the knowledge representation technique of Decisional DNA. This blend of the virtual and physical domains permits monitoring of systems and analysis of data to foresee problems before they occur, develop new opportunities, prevent downtime, and even plan for the future by using simulations. Furthermore, the proposed virtual model concept not only has the capability of Query Processing and Data Integration for Industrial Data but also real-time visualization of data stream processing.     

Models for circular data from time series spectra

Circular data are those for which the natural support is the unit circle and its toroidal extensions. Numerous constructions have been proposed which can be used to generate models for such data. We propose a new, very general, one based on the normalization of the spectra of complex-valued stationary processes. As illustrations of the new construction's application, we study models for univariate circular data obtained from the spectra of autoregressive moving average models and relate them to existing models in the literature. We also propose and investigate multivariate circular models obtained from the high-order spectra of stationary stochastic processes generated using linear filtering with an autoregressive moving average response function. A new family of distributions for a Markov process on the circle is also introduced. Results for asymptotically optimal inference for dependent observations on the circle are presented which provide a new paradigm for inference with circular models. The application of one of the new families of spectra-generated models is illustrated in an analysis of wind direction data.     

A method to infer the need to update situations in business process adaptation

Contextual knowledge is an essential resource for adapting business processes in order to keep them aligned with its goals. A context-based adaptation environment should learn from the dynamism of the context as well as the decisions made, and continuously identify new unforeseen situations. Data mining is a possibility to maintain the analysis of the processes updated. This paper presents a method that infers the need to learn new situations that influence a business process execution. The method is based on the results of the Apriori algorithm application. Case studies were conducted to evaluate the proposal. We observed evidences of context changes over time and the potential to learn with this dynamics through the method proposed.     

Catalytic Evaluation of CuO/[Si]MCM‐41 in Fenton‐like Reactions

CuO/[Si]MCM‐41 catalysts with various Si/Cu molar ratios were prepared and characterized by X‐ray diffraction, nitrogen physisorption, temperature‐programmed reduction by H₂, and UV‐vis and Raman spectroscopy. The effects of copper loading and pH on their activity in the decolorization of methyl orange were studied in a heterogeneous Fenton‐like process. With decreasing Si/Cu ratio, dye decolorization increased from 18 to 75 % at pH 3. CuO/[Si]MCM‐41 catalysts showed 75, 50, and 40 % conversion of methyl orange at pH 3, 5, and 7, respectively. This is a significant improvement to Fenton‐like reactions involving copper, and thus CuO/[Si]MCM‐41 catalysts are quite promising for pollutant degradation.