Towards artificial intelligence at scale in the chemical industry

In the Industry 4.0 era, the chemical industry is embracing broad adoption of artificial intelligence (AI) and machine learning (ML) methods. This article provides a holistic view of how the industry is transforming digitally towards AI at scale. First, a historical perspective on how the industry used AI to aid humans in better decision-making is shown. Then state-of-the-art AI research addressing industrial needs on reliability and safety, process optimization, supply chain, material discovery, and reaction engineering is highlighted. Finally, a vision of the plant of the future is illustrated with critical components of AI-ready culture, model life cycle management, and renewed role of humans in chemical manufacturing.     

Enhanced structural,electromagnetic and absorption features of CoSm ferrite-metamaterial absorbers through synergistic effects

Currently, materials with outstanding absorption abilities, such as thin size, better absorbing power, and light weight are the need of industry to resolve the electromagnetic issues. However, the research on optimizing the composition of the material, microstructure and the structure of the absorber are also the important factors for enhancing the absorption features. A metamaterial microwave absorber (MMA) based on nano ferrites with desirable absorption peaks is proposed and simulated. Sol-gel auto combustion route is used to prepare the nanosized Sm doped Co ferrite with Co_1+xSm_xFe_2-2xO₄ at x = 0.00, 0.03, 0.06, 0.09, respectively. XRD, VSM, FESEM, and VNA were employed to evaluate the structural, magnetic, morphological, and dielectric features. Rietveld refinement of the XRD patterns of samples was evaluated. Refined parameters show the spinel phase's emergence and the Fe₂O₃ phase. Grain size and crystallite size were increased with Sm doping in Co ferrite. Electromagnetic studies depicted that the highest dielectric constant value was found at x = 0.09 and the minimum value at x = 0.03, respectively. Sm doped Co ferrite at x = 0.09 depicted high Q values at higher frequencies. The coercivity values first decreased and then increased. All samples exhibit variations in coercivity and magneto-crystalline anisotropy constant. This variation was attributed to the super-exchange interactions and strong LS coupling of the cations. The multiple absorption peaks are attained for TE-polarization, and the absorptivity is considerably improved for x = 0.09. The proposed absorber simulated from CST depicted the absorption peaks of the S-band and C-band of the microwave regime. The synergistic effects among the metamaterial and ferrite layers may enhance the absorption feature and would be useful for satellite communication applications.     

基于改进相干增强扩散与纹理能量测度和高斯混合模型的导光板表面缺陷检测方法

针对液晶屏(LCD)导光板表面缺陷检测方法存在漏检率和误检率较高,对产品表面复杂渐变的纹理结构适应性差的问题,提出一种基于改进相干增强扩散(ICED)与纹理能量测度和高斯混合模型(TEM-GMM)的LCD导光板表面缺陷检测方法。首先,构建ICED模型,基于结构张量引入平均曲率流扩散(MCF)滤波,使得相干增强扩散(CED)模型对缺陷的细线状纹理有良好的边缘保持效果,并利用相干性得到缺陷纹理增强和背景纹理抑制的滤波后图像;然后,根据Laws纹理能量测度(TEM)提取图像纹理特征,将图像的背景纹理特征作为离线阶段高斯混合模型(GMM)的训练数据,使用期望最大化(EM)算法估计GMM参数;最后,计算待检测图像各像素的后验概率,并将其作为在线检测阶段缺陷像素的判断依据。实验结果表明,该检测方法在导光颗粒随机、规则两种分布的缺陷图像测试数据组上的漏检率和误检率分别为3.27%、4.32%和3.59%、4.87%。所提检测方法适用范围广,可有效检测出LCD导光板表面划痕、异物、脏污和压伤等类型的缺陷。     

Preparation of P(St-NMA) microsphere inks and their application in photonic crystal patterns with brilliant structural colors

Patterned photonic crystals with structural colors on textile substrates have attracted a special attention due to the great advantages in application, which currently become a research hot-spot. This study utilized an ink-jet printing technology to prepare high-quality photonic crystal patterns with structural colors on polyester substrates. The self-assembly temperature of poly(styrene-N-methylol acrylamide) (P(St-NMA)) microspheres set to construct photonic crystals were deeply optimized. Moreover, the structural colors of prepared photonic crystal patterns were characterized and evaluated. When the mass fraction of P(St-NMA) microspheres was 1.0 wt.%, the pH value ranged from 5 to 7, and the surface tension was in the range of 63.79 to 71.20 mN/m, inks could present the best print performance. At 60 °C, prepared P(St-NMA) microsphere inks were good for printing to obtain patterned photonic crystals with regular arrangement and beautiful structural colors. Specifically, photonic crystals with different colors could be constructed by regulating the diameter of microspheres in inks, and prepared structural colors exhibited distinct iridescent phenomenon. The present results could provide a theoretical basis for the industrial realization of patterned photonic crystals by ink-jet printing technology.     

碳酸性侵蚀与AAR作用下纳米混凝土的耐久性

地铁混凝土处于地下空间,容易受到地下水的碳酸性侵蚀；碱集料反应 (AAR)是一种严重的混凝土耐久性问题,既难以发现又难以修补,由两者共同作用引起的混凝土耐久性降低严重影响地铁隧道的正常使用.为研究纳米材料对地铁混凝土在碳酸性侵蚀和AAR共同作用下耐久性的影响,在普通混凝土中掺入适量纳米SiO₂和纳米Fe₂O₃,利用自行研制的碳酸性侵蚀试验箱进行试验,采用碳酸性侵蚀深度、膨胀率和声速作为测试指标来评价纳米混凝土在碳酸性侵蚀和AAR共同作用下的耐久性.试验结果表明:掺入纳米颗粒后,混凝土的膨胀率和侵蚀深度有了明显降低,而声速有了明显提升,说明纳米混凝土的耐久性优于普通混凝土；在182 d龄期时,掺量为2%的纳米SiO₂混凝土耐久性改善最明显,侵蚀深度和膨胀率最小,声速最大且声速下降幅度最小；其次是掺量为1%的纳米Fe₂O₃混凝土.由于纳米颗粒特殊的物理化学性质,改善了混凝土内部的微观结构和孔溶液的化学组成,使碳酸性侵蚀和碱集料反应共同作用下混凝土的耐久性得到了提高.     

Identification,Phylogeny, and Comparative Expression of the Lipoxygenase Gene Family of the Aquatic Duckweed,Spirodela polyrhiza,during Growth and in Response to Methyl Jasmonate and Salt

Lipoxygenases (LOXs) (EC 1.13.11.12) catalyze the oxygenation of fatty acids and produce oxylipins, including the plant hormone jasmonic acid (JA) and its methyl ester, methyl jasmonate (MeJA). Little information is available about the LOX gene family in aquatic plants. We identified a novel LOX gene family comprising nine LOX genes in the aquatic plant Spirodela polyrhiza (greater duckweed). The reduced anatomy of S. polyrhiza did not lead to a reduction in LOX family genes. The 13-LOX subfamily, with seven genes, predominates, while the 9-LOX subfamily is reduced to two genes, an opposite trend from known LOX families of other plant species. As the 13-LOX subfamily is associated with the synthesis of JA/MeJA, its predominance in the Spirodela genome raises the possibility of a higher requirement for the hormone in the aquatic plant. JA-/MeJA-based feedback regulation during culture aging as well as the induction of LOX gene family members within 6 h of salt exposure are demonstrated.     

Fabrication and Characterization of Highly Oriented Composite Nanofibers with Excellent Mechanical Strength and Thermal Stability

Here, highly‐oriented poly(m‐phenylene isophthalamide)/polyacrylonitrile multi‐walled carbon nanotube (PMIA/PAN‐MWCNT) composite nanofiber membranes with excellent mechanical strength and thermal stability are successfully produced using electrospinning. It is demonstrated that the cooperation of multi‐walled carbon nanotubes (MWCNT) and high‐speed rotating collection is beneficial to the acquisition of highly oriented fibers and effectively improves the mechanical strength of the membrane along the orientation direction. Specifically, the tensile stress of poly(m‐phenylene isophthalamide)/polyacrylonitrile (PMIA/PAN) membrane is enhanced significantly from 10.6 to 20.7 MPa, benefiting from the highly oriented alignment of the fibers as well as the reinforcing effect of MWCNTs on the fibers. Furthermore, the stressing process of single fiber and fiber aggregates is carefully simulated, and the influence of MWCNTs on the mechanical properties of PMIA/PAN‐MWCNT membranes is analyzed comprehensively, providing a meaningful auxiliary means for the study of mechanical properties. In addition, the composite nanofiber membrane has the advantages of both PMIA and PAN, possessing high temperature resistance, flame‐retardancy, and chemical stability, for an ideal high‐temperature material. In short, the as‐prepared PMIA/PAN‐MWCNT composite membrane with excellent comprehensive property emerges a promising application in many fields, especially in high‐tech.     

咖啡渣活性炭的制备、表征及其对Cr(Ⅵ)的吸附机制研究

以碘吸附值为评价指标，活化时间、活化温度和浸渍比为影响因素，采用响应面法试验设计对磷酸活化法制备咖啡渣活性炭的工艺条件进行优化，并通过静态吸附试验研究了不同吸附时间、溶液pH值和吸附温度条件下，活性炭对水溶液中Cr（Ⅵ）吸附性能的影响，最后利用Langmuir、Freundlich吸附等温方程、准一级动力学方程、准二级动力学方程和颗粒内部扩散方程进行拟合。试验结果表明，制备咖啡渣活性炭的最佳工艺条件为活化时间1 h、活化温度498℃、浸渍比1.72；在此条件下活性炭得率为30.4%，碘吸附值为（799±16）mg/g，比表面积为1 006 m²/g，孔容为0.779 cm³/g、微孔孔容为0.051 cm³/g、平均孔径为3.088 nm。较低pH值和较高温度能够促进活性炭对Cr（Ⅵ）的吸附；Langmuir等温方程能够更好地描述活性炭对Cr（Ⅵ）的吸附效果；活性炭对Cr（Ⅵ）的吸附分3个阶段：快速吸附阶段、慢速吸附阶段和吸附平衡阶段，10 min内可完成吸附总量的79%，360 min内达到吸附平衡，该吸附过程符合准二级吸附动力学方程。分析表明咖啡渣活性炭对Cr（Ⅵ）的吸附主要为单分子层的化学吸附。     

Imidazolium functionalized poly(vinyl alcohol) membranes for direct methanol alkaline fuel cell applications

In this study, imidazolium functionalized poly(vinyl alcohol) (PVA) was synthesized by acetalization and direct quaternization reaction. Afterwards, composite anion exchange membranes based on imidazolium‐ and quaternary ammonium‐ functionalized PVA were used for direct methanol alkaline fuel cell applications. ¹H NMR and Fourier transform infrared spectroscopy data indicated that imidazole functionalized PVA was successfully synthesized. Inductively coupled plasma mass spectrometry data demonstrated that the imidazolium structure was efficiently obtained by direct quaternization of the imidazole group. Composite anion exchange membranes were fabricated by application of the functionalized PVA solution on the surface of porous polycarbonate (PC) membranes. Fuel cell related properties of all prepared membranes were investigated systematically. The imidazolium functionalized composite membrane (PVA‐Im/PC) exhibited higher ionic conductivity (7.8 mS cm^?1 at 30 °C) despite a lower water uptake and ion exchange capacity value compared to that of quaternary ammonium. In addition, PVA‐Im/PC showed the lowest methanol permeation rate and the highest membrane selectivity as well as high alkaline and oxidative stability. Dynamic mechanical analysis results reveal that both composite membranes were mechanically resistant up to 10⁷ Pa at 140 °C. The superior performance of imidazolium functionalized PVA composite membrane compared to quaternary ammonium functionalized membrane makes it a promising candidate for direct methanol alkaline fuel cell applications. © 2020 Society of Chemical Industry     

基于LP与小波包的复杂机电系统监测序列混沌降噪方法

针对流程工业生产系统监测数据存在强噪声和混沌性的特点,提出了一种局部投影方法(Local Projection Method)与小波包方法相结合的信号降噪方法。该方法先利用局部投影方法从动力学系统嵌入流形的角度进行多次迭代降噪,并根据关联维数来判定迭代终止;再利用小波包方法从频率的角度进行降噪,抑制高频噪声的干扰,取得了较好的降噪效果。用Lorenz时间序列进行仿真验证,对仿真时间序列加入不同程度的噪声,对比分析小波包、局部投影与该方法降噪后的相空间、SNR值和最大Lyapunov指数,证明了该方法对于中高强度噪声具有更好的降噪效果。并将该方法用于某压缩机组的实际监测数据降噪,评估三种方法的降噪效果,进一步验证了该方法的优越性。