An overview on fault diagnosis and nature-inspired optimal control of industrial process applications

Fault detection, isolation and optimal control have long been applied to industry. These techniques have proven various successful theoretical results and industrial applications. Fault diagnosis is considered as the merge of fault detection (that indicates if there is a fault) and fault isolation (that determines where the fault is), and it has important effects on the operation of complex dynamical systems specific to modern industry applications such as industrial electronics, business management systems, energy, and public sectors. Since the resources are always limited in real-world industrial applications, the solutions to optimally use them under various constraints are of high actuality. In this context, the optimal tuning of linear and nonlinear controllers is a systematic way to meet the performance specifications expressed as optimization problems that target the minimization of integral- or sum-type objective functions, where the tuning parameters of the controllers are the vector variables of the objective functions. The nature-inspired optimization algorithms give efficient solutions to such optimization problems. This paper presents an overview on recent developments in machine learning, data mining and evolving soft computing techniques for fault diagnosis and on nature-inspired optimal control. The generic theory is discussed along with illustrative industrial process applications that include a real liquid level control application, wind turbines and a nonlinear servo system. New research challenges with strong industrial impact are highlighted.     

Human responses to high levels of carbon dioxide and air temperature

In this study, 30 subjects were exposed to different combinations of air temperature (T_a: 24, 27, and 30°C) and CO₂ level (8000, 10 000, and 12 000 ppm) in a high-humidity (RH: 85%) underground climate chamber. Subjective assessments, physiological responses, and cognitive performance were investigated. The results showed that as compared with exposure to T_a = 24°C, exposure to 30°C at all CO₂ levels caused subjects to feel uncomfortably warm and experience stronger odor intensity, while increased mental effort and greater intensity of acute health symptoms were reported. However, no significant effects of T_a on task performance or physiological responses were found. This indicated that subjects had to exert more effort to maintain their performance in an uncomfortably warm environment. Increasing CO₂ from 8000 to 12 000 ppm at all T_a caused subjects to report higher rates of headache, fatigue, agitation, and feeling depressed, although the results were statistically significant only at 24 and 27°C. The text typing performance and systolic blood pressure (SBP) decreased significantly at this exposure, whereas diastolic blood pressure (DBP) and thermal discomfort increased significantly. These effects suggest higher arousal/stress. No significant interaction effect of T_a and CO₂ concentration on human responses was identified.     

Effect of Li2O on the crystallization behavior of CaO-Al2O3-SiO2-Li2O-Ce2O3 mold slags

The effect of Li₂O on the crystallization properties of CaO-Al₂O₃-SiO₂-Li₂O-Ce₂O₃ slags was investigated. With increasing the Li₂O content, LiAlO₂ and CaCeAlO₄ were the main crystalline phases. LiAlO₂ formed for the charge compensating of Li⁺ ions to [AlO₄^5?]-tetrahedrons, and CaCeAlO₄ formed as a result of the charge balance of Ce³⁺ ions, Ca²⁺ ions, and [AlO₆^9?]-octahedrons. Increasing the content of Li₂O to 10%, the crystallization temperature was the highest, and the incubation time was the shortest. The crystallization ability was strong due to the three factors of strengthening the interaction between ions and ion groups, decreasing the polymerization degree, and increasing the melting temperature. Further increasing the content of Li₂O, the crystallization performance was obviously suppressed, because the melting temperature and the force between the cations and the anion groups decreased.     

Electrospun fiber membranes from blends of poly(vinylidene fluoride) with fouling‐resistant zwitterionic copolymers

Nonwoven super‐hydrophobic fiber membranes have potential applications in oil–water separation and membrane distillation, but fouling negatively impacts both applications. Membranes were prepared from blends comprising poly(vinylidene fluoride) (PVDF) and random zwitterionic copolymers of poly(methyl methacrylate) (PMMA) with sulfobetaine methacrylate (SBMA) or with sulfobetaine‐2‐vinylpyridine (SB2VP). PVDF imparts mechanical strength to the membrane, while the copolymers enhance fouling resistance. Blend composition was varied by controlling the PVDF‐to‐copolymer ratio. Nonwoven fiber membranes were obtained by electrospinning solutions of PVDF and the copolymers in a mixed solvent of N,N‐dimethylacetamide and acetone. The PVDF crystal phases and crystallinities of the blends were studied using wide‐angle X‐ray diffraction and differential scanning calorimetry (DSC). PVDF crystallized preferentially into its polar β‐phase, though its degree of crystallinity was reduced with increased addition of the random copolymers. Thermogravimetry (TG) showed that the degradation temperatures varied systematically with blend composition. PVDF blends with either copolymer showed significant increase of fouling resistance. Membranes prepared from blends containing 10% P(MMA‐ran‐SB2VP) had the highest fouling resistance, with a fivefold decrease in protein adsorption on the surface, compared to homopolymer PVDF. They also exhibited higher pure water flux, and better oil removal in oil–water separation experiments. © 2018 Society of Chemical Industry     

Prediction of risk factors of cyberbullying-related words in Korea: Application of data mining using social big data

The study examined a decision tree analysis using social big data to conduct the prediction model on types of risk factors related to cyberbullying in Korea. The study conducted an analysis of 103,212 buzzes that had noted causes of cyberbullying and data were collected from 227 online channels, such as news websites, blogs, online groups, social network services, and online bulletin boards. Using opinion-mining method and decision tree analysis, the types of cyberbullying were sorted using SPSS 25.0. The results indicated that the total rate of types of cyberbullying in Korea was 44%, which consisted of 32.3% victims, 6.4% perpetrators, and 5.3% bystanders. According to the results, the impulse factor was also the greatest influence on the prediction of the risk factors and the propensity for dominance factor was the second greatest factor predicting the types of risk factors. In particular, the impulse factor had the most significant effect on bystanders, and the propensity for dominance factor was also significant in influencing online perpetrators. It is necessary to develop a program to diminish the impulses that were initiated by bystanders as well as victims and perpetrators because many of those bystanders have tended to aggravate impulsive cyberbullying behaviors.     

Characterization,in vitro bioactivity and biological studies of sol-gel-derived TiO2 substituted 58S bioactive glass

Bioactive glasses (BGs) have been used for bone formation and bone repair processes in recent years. This study investigated the titanium substitution effect on 58S BGs (Ti-BGs) 60SiO₂-(36 − X)CaO-4P₂O₅-XTiO₂ (X = 0, 3, and 5 mol.%) prepared by the sol-gel technique, and the main goal was to find the optimum amount of titanium in Ti-BGs. Synthesized BGs, which were investigated after immersion in simulated body fluid (SBF), were tested by X-ray diffraction (XRD) analysis, Fourier transform infrared spectroscopy (FTIR), and scanning electron microscopy. Moreover alkaline phosphate (ALP) activity, 3-(4,5dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide (MTT) assay, and antibacterial studies were employed to investigate the biological properties of Ti-BGs. According to the FTIR and XRD test results, hydroxyapatite (HA) formation on Ti-BGs surfaces was confirmed. Meanwhile, the presence of 5 mol.% compared to 3 mol.% increased the HA grain distribution and their size on the Ti-BGs surface. Additionally, MTT and ALP results confirmed that the optimal amount of titanium substitution in BG was 5 mol.%. Since 5 mol.% Ti incorporated BG (BG-5) had the highest biocompatibility level, antibacterial properties, maximum cell proliferation, and ALP activity among the synthesized Ti-BGs, it is presented as the best candidate for further in vivo investigations.     

基于微博用户兴趣话题的相似用户挖掘

相似用户挖掘是提高社交网络服务质量的重要途径，在面向大数据的社交网络时代，准确的相似用户挖掘对于用户和互联网企业等都有重要的意义，而根据用户自己的兴趣话题挖掘的相似用户更符合相似用户的要求。提出了一种基于用户兴趣话题进行相似用户挖掘的方法。该方法首先使用TextRank话题提取方法对用户进行兴趣话题提取，再对用户发表内容进行训练，计算出所有词之间的相似度。提出CP（Corresponding Position similarity）、CPW（Corresponding Position Weighted similarity）、AP（All Position similarity）、APW（All Position Weighted similarity）四种用户兴趣话题词相似度计算方法，通过用户和相似用户间关注、粉丝重合率验证相似用户挖掘效果，APW similarity的相似用户的关注/粉丝重合百分比为1.687%，优于提出的其他三种算法，分别提高了26.3%、2.8%、12.4%，并且比传统的文本相似度方法Jaccard相似度、编辑距离算法、余弦相似度分别提高了20.4%、21.2%、45.0%。因此APW方法可以更加有效地挖掘出用户的相似用户。     

Red-shift and improved afterglow of Sr3Al2-xBxO5Cl2:Eu2+, Dy3+ phosphors via a cation substitution strategy

Sr₃Al_2-xB_xO₅Cl₂:Eu²⁺, Dy³⁺ (x = 0, 0.2, 0.4) long persistent phosphors were prepared via solid-state process. The pristine Sr₃Al₂O₅Cl₂:Eu²⁺, Dy³⁺ phosphor exhibits orange/red broad band emission around 609 nm, which can be attributed to the electric radiation transitions 4f⁶5 d¹→4f⁷ of Eu²⁺. Upon the same excitation, the B³⁺-doped Sr₃Al_2-xB_xO₅Cl₂:Eu²⁺, Dy³⁺ phosphors display red-shift from 609 nm to 625 nm with increasing B³⁺ concentrations. The XRD patterns show that Al³⁺ can be replaced by B³⁺ in the host lattice at the tetrahedral site, which causes lattice contraction and crystal field enhancement, and thereafter achieves the red-shift on the emission spectrum. The XPS investigation provides direct evidence of the dominant 2-valent europium in the phosphor, which can be ascribed for the broad band emission of the prepared phosphors. The afterglow of all phosphors show standard double exponential decay behavior, and the afterglow of Sr₃Al₂O₅Cl₂:Eu²⁺, Dy³⁺is rather weak, while the sample co-doped with B³⁺shows longer and stronger afterglow, as confirmed after the curve simulation. The analysis of thermally stimulated luminescence showed that, when B³⁺ is introduced, a much deeper trap is created, and the density of the electron trap is also significantly increased. As a result, B³⁺ ions caused redshift and enhanced afterglow for the Sr₃Al_2-xB_xO₅Cl₂:Eu²⁺, Dy³⁺ phosphor.     

A single-phase algorithm for mining high utility itemsets using compressed tree structures

Mining high utility itemsets (HUIs) from transaction databases considers such factors as the unit profit and quantity of purchased items. Two-phase tree-based algorithms transform a database into compressed tree structures and generate candidate patterns through a recursive pattern-growth procedure. This procedure requires a lot of memory and time to construct conditional pattern trees. To address this issue, this study employs two compressed tree structures, namely, Utility Count Tree and String Utility Tree, to enumerate valid patterns and thus promote fast utility computation. Furthermore, the study presents an algorithm called single-phase utility computation (SPUC) that leverages these two tree structures to mine HUIs in a single phase by incorporating novel pruning strategies. Experiments conducted on both real and synthetic datasets demonstrate the superior performance of SPUC compared with IHUP, UP-Growth, and UP-Growth+ algorithms.     

TiO2/MXene-Assisted LDI-MS for Urine Metabolic Profiling in Urinary Disease

Cancer remains an intractable medical problem. Rapid diagnosis and identification of cancer are critical to differentiate it from nonmalignant diseases. High-throughput biofluid metabolic analysis has potential for cancer diagnosis. Nevertheless, the present metabolite analysis method does not meet the demand for high-throughput screening of diseases. Herein, a high-throughput, cost-effective, and noninvasive urine metabolic profiling method based on TiO₂/MXene-assisted laser desorption/ionization mass spectrometry (LDI-MS) is presented for the efficient screening of bladder cancer (BC) and nonmalignant urinary disease. Combined with machine learning, TiO₂/MXene-assisted LDI-MS enables high diagnostic accuracy (96.8%) for the classification of patient groups (including 47 BC and 46 ureteral calculus (UC) patients) from healthy controls (113 cases). In addition, BC patients can also be identified from noncancerous UC individuals with an accuracy of 88.3% in the independent test cohort. Furthermore, metabolite variations between BC and UC individuals are investigated based on relative quantification, and related pathways are also discussed. These results suggest that this method, based on urine metabolic patterns, provides a potential tool for rapidly distinguishing urinary diseases and it may pave the way for precision medicine.