Predictive maintenance (PM) algorithms are widely applied for detecting operational anomalies on industrial processes to schedule for a maintenance intervention before a possible breakdown; however, much less focus has been devoted to the use of such prognostics in process scheduling. The existing solutions mostly integrate preventive approaches to protect the machines, usually causing downtimes. The premise of this study is to develop a process scheduling mechanism that selects an acceptable operating condition for an industrial process to adapt to the predicted anomalies. As PM is largely a data-driven approach (hence, it relies on the setup), we first compare different PM approaches and identify a one-class support vector machine (OCSVM) as the best performing option for the anomaly detection on our setup. Then, we propose a novel pipeline to integrate maintenance predictions into a real-time, adaptive process scheduling mechanism. According to the abnormal readings, it schedules for the most suitable operation, i.e., optimizing for machine health and process efficiency, toward preventing breakdowns while maintaining its availability and operational state, thereby reducing downtimes. To demonstrate the pipeline on the action, we implement our approach on a small-scale conveyor belt, utilizing our Internet of Things (IoT) framework. The results show that our PM-based adaptive process control retains an efficient process under abnormal conditions with less or no downtime. We also conclude that a PM approach does not provide sufficient efficiency without its integration into an autonomous planning process.

Based on the characteristic of cell voltage fluctuations in the process of electrolytic aluminum, a new method based on neural-network-genetic-algorithm (NNGA) for the optimization of cell voltage is proposed in this paper. First, the method of kernel principal component based on analysis of electrolytic aluminum process is used to determine the operating parameters. Second, in order to predict cell voltage in real time, back propagation neural network (BPNN) is used to establish the cell voltage prediction model. Third, the model of the optimization control of cell voltage is constructed, and then, genetic algorithm is used to optimize cell voltage and obtain corresponding operating conditions. Finally, the actual production data is used to perform experimental verification. The results show that the proposed method based on NNGA is effective. The process of electrolytic aluminum can operate under the optimal production conditions, and the goal of saving energy is achieved.

No abstract

The interplay between non-trivial band topology and magnetic order can induce exotic quantum phenomena, such as the quantum anomalous Hall effect and axion insulator state. A prevalent approach to realizing such topological states is either by magnetic doping or through heterostructure engineering, while the former will bring in inhomogeneity and the latter requires complex procedures. Intrinsic magnetic topological insulators are expected to avoid the aforementioned disadvantages, which is of great significance in both studying and practically using these exotic quantum phenomena. Recently, a Zintl compound EuIn₂As₂ is predicted to be an intrinsic antiferromagnetic axion insulator. The bulk magnetic order of EuIn₂As₂ has been reported in a lot of experiments, while the topological nature has not yet been confirmed. The surface properties of intrinsic magnetic topological insulators play an important role in the interplay between magnetic order and non-trivial surface state. Here in this work, we study the surface structure and electronic property of EuIn₂As₂ single crystal by using scanning tunneling microscopy/spectroscopy (STM/S) and non-contact atomic force microscopy (NC-AFM). Considering the strength of bonds, the easy cleavage plane of the crystals possibly lies between In-In layers or between Eu-As layers. The STM topographies show that the cleaved surface is dominated by a striped pattern. And the dominated step height is an integer multiple of <i>c</i>/2, which implies that only one kind of cleavage plane is preferred. Atomic-resolved surface topographies show that the striped pattern is the <inline-formula><tex-math id="M2">\begin{document}$ 1\times 2 $\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20210783_M2.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20210783_M2.png"/></alternatives></inline-formula> surface reconstruction with 50% coverage. Hence an In-terminated surface which will be 100% coverage is ruled out. The spatial evolution of STS near vacancies on the striped pattern shows a hole-doping feature. All of these results reveal that the striped pattern is the <inline-formula><tex-math id="M3">\begin{document}$ 1\times 2 $\end{document}</tex-math><alternatives><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20210783_M3.jpg"/><graphic xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="18-20210783_M3.png"/></alternatives></inline-formula> surface reconstruction of the Eu terminated surface with 50% coverage. Using the STS, we measure the local densities of states on the striped surface at various temperatures. We find that there is an asymmetric valley-peak feature in the density of states near the Fermi energy at 4 K, which is gradually weakened with increasing temperature, and disappears above the antiferromagnetic Néel temperature, indicating that the asymmetric valley-peak feature is closely related to the antiferromagnetic order. Besides, a maze-like pattern is observed occasionally near some step edges. The STM topographies show atoms both on bright and dark stripes of the maze-like pattern, which form a whole hexagonal lattice. And the NC-AFM images show that the maze-like pattern is about 1 Å higher than the Eu terminated striped pattern. Based on these results, the maze-like pattern can be explained as the buckled Eu surface with 100% coverage. These results provide important information for understanding the surface electronic band structure and topological nature of EuIn₂As₂.

Fault characteristic frequency is the main basis for rolling element bearing diagnostics but finding a suitable frequency band for demodulation and searching for the fault characteristic frequencies consume a lot of time and manpower in practice. A data-driven method based on recursive variational mode decomposition (RVMD), and an envelope order capture is proposed to realize the automatic fault diagnosis of bearing under different operating conditions. The process starts with a new proposed RVMD of the vibration signal, where the mode with maximum kurtosis of the unbiased autocorrelation of the envelope is selected to get envelope order spectrum. Thereafter, an order capture algorithm is designed to automatically search for the fault characteristic orders in theory, which are used for constructing feature vectors for diagnosis. The proposed method is tested on two test-beds which both contain the same type of bearing (SKF6205) but operate in different conditions, and gets good performance in bearing diagnosis. In addition, the fault diagnosis of test-bed two using training samples that are from test-bed one is investigated. This method reveals well generalization capability in the fault diagnosis of the same type of rolling element bearing under different operating conditions. INDEX TERMS Rolling element bearing, automatic fault diagnosis, recursive variational mode decomposition, envelope order capture.