Fine-Grained Multivariate Time Series Anomaly Detection in IoT

Sensors produce a large amount of multivariate time series data to record the states of Internet of Things (IoT) systems. Multivariate time series timestamp anomaly detection (TSAD) can identify timestamps of attacks and malfunctions. However, it is necessary to determine which sensor or indicator is abnormal to facilitate a more detailed diagnosis, a process referred to as fine-grained anomaly detection (FGAD). Although further FGAD can be extended based on TSAD methods, existing works do not provide a quantitative evaluation, and the performance is unknown. Therefore, to tackle the FGAD problem, this paper first verifies that the TSAD methods achieve low performance when applied to the FGAD task directly because of the excessive fusion of features and the ignoring of the relationship’s dynamic changes between indicators. Accordingly, this paper proposes a multivariate time series fine-grained anomaly detection (MFGAD) framework. To avoid excessive fusion of features, MFGAD constructs two sub-models to independently identify the abnormal timestamp and abnormal indicator instead of a single model and then combines the two kinds of abnormal results to detect the fine-grained anomaly. Based on this framework, an algorithm based on Graph Attention Neural Network (GAT) and Attention Convolutional Long-Short Term Memory (A-ConvLSTM) is proposed, in which GAT learns temporal features of multiple indicators to detect abnormal timestamps and A-ConvLSTM captures the dynamic relationship between indicators to identify abnormal indicators. Extensive simulations on a real-world dataset demonstrate that the proposed algorithm can achieve a higher F1 score and hit rate than the extension of existing TSAD methods with the benefit of two independent sub-models for timestamp and indicator detection.     

Study on dislocation density,microstructure, and mechanical properties of P92 steel for different heat treatment conditions

The impact of various heat treatment procedures on microstructure, dislocation density, hardness, tensile characteristics, and impact toughness of P92 steel was examined in the current experiment. The martensitic microstructure and average microhardness of 463 HV 0.2±8 HV 0.2 of the normalized steel were prevalent. A tempering procedure was carried out at 760 °C for a range of 2 hours to 6 hours. Additionally, an X-ray diffraction examination was carried out, and the results were used to determine the dislocation density. The normalized sample was characterized by a high dislocation density. The dislocation density was decreased by tempering of normalized samples. With an increase in tempering time, the effect of the treatment coarsened the grains, precipitates, and decreased the area fraction of precipitates. After tempering, MX, M₂₃C₆, and M₇C₃ types precipitates were found to have precipitated, according to energy dispersive spectroscopy and x-ray diffraction research. The ideal tempering period was determined to be 4 hours at a tempering temperature of 760 °C based on the microstructure and mechanical characteristics. Steel that was tempered at 760 °C for 4 hours had a yield strength of 472 MPa, an ultimate tensile strength of 668.02 MPa, and an elongation of 26.05 %, respectively.     

Sol-gel processed barium titanate ceramics and thin films

Ferroelectric barium titanate (BaTiO3) ceramics and thin films have been prepared from barium acetate (Ba(CH3COO)2) and titanium (IV) isopropoxied (Ti((CH3)2CHO)4) precursors by a sol–gel technique. The as-grown powder and thin films were found to be amorphous, which crystallized to the tetragonal phase after annealing at 700°C in air for 1 h. Both the ceramics and thin films showed well-saturated polarization–field (P–E) hysteresis loops at room temperature. The value of the spontaneous polarization, PS, remnant polarization, Pr, and coercive field, Ec, of the ceramics and thin films determined from the P–E hysteresis loop were found to be 19.0 and 12.6; 14.0 and 3.2 G cm–2, and 30 and 53 kV cm–1, respectively. The coercive field of the film determined from the capacitance–voltage, C–V, characteristics is slightly lower than that determined from the P–E hysteresis loop (43 kV cm–1). The room-temperature dielectric constant, , of the ceramics and films was found to be 1135 and 370, respectively. Both the films and ceramics showed dielectric anomaly peaks at 125 °C, showing ferroelectric to paraelectric phase transition. © 1998 Kluwer Academic Publishers     

Chromatic aberrations of radial gradient-index lenses. I. Theory

Chromatic effects of radial gradient-index materials have been analyzed, and several important conclusions have been derived in terms of material dispersion data. The use of Buchdahl dispersion data, both for base glass materials and ion-exchange pairs, provides some simple relationships for chromatic aberration and helps in selecting suitable materials for producing achromatic radial gradient-index lenses.     

Rolling element bearing fault diagnosis using wavelet transform

This paper is focused on fault diagnosis of ball bearings having localized defects (spalls) on the various bearing components using wavelet-based feature extraction. The statistical features required for the training and testing of artificial intelligence techniques are calculated by the implementation of a wavelet based methodology developed using Minimum Shannon Entropy Criterion. Seven different base wavelets are considered for the study and Complex Morlet wavelet is selected based on minimum Shannon Entropy Criterion to extract statistical features from wavelet coefficients of raw vibration signals. In the methodology, firstly a wavelet theory based feature extraction methodology is developed that demonstrates the information of fault from the raw signals and then the potential of various artificial intelligence techniques to predict the type of defect in bearings is investigated. Three artificial intelligence techniques are used for faults classifications, out of which two are supervised machine learning techniques i.e. support vector machine, learning vector quantization and other one is an unsupervised machine learning technique i.e. self-organizing maps. The fault classification results show that the support vector machine identified the fault categories of rolling element bearing more accurately and has a better diagnosis performance as compared to the learning vector quantization and self-organizing maps.     

Artificial neural network based system identification and model predictive control of a flotation column

The paper describes the design of a neural network based model predictive controller for controlling the interface level in a flotation column. For the system identification, the tailings valve opening is subjected to a pseudo-random ternary signal and response of the interface level is recorded over a period of time. The data so generated is used to develop a dynamic feed forward neural network model. The model uses two past values and one present value of the tailings valve opening as well as interface level as inputs and predicts the future interface level. This model is used for the design of a model predictive controller to control the interface level. The controller was tested both for liquid–gas system as well as liquid–gas–solid system and was found to perform very satisfactorily. The performance of the controller was compared with that of a conventional PI controller for a two-phase system and was found to be better.     

Lévy flight artificial bee colony algorithm

Artificial bee colony (ABC) optimisation algorithm is a relatively simple and recent population-based probabilistic approach for global optimisation. The solution search equation of ABC is significantly influenced by a random quantity which helps in exploration at the cost of exploitation of the search space. In the ABC, there is a high chance to skip the true solution due to its large step sizes. In order to balance between diversity and convergence in the ABC, a Lévy flight inspired search strategy is proposed and integrated with ABC. The proposed strategy is named as Lévy Flight ABC (LFABC) has both the local and global search capability simultaneously and can be achieved by tuning the Lévy flight parameters and thus automatically tuning the step sizes. In the LFABC, new solutions are generated around the best solution and it helps to enhance the exploitation capability of ABC. Furthermore, to improve the exploration capability, the numbers of scout bees are increased. The experiments on 20 test problems of different complexities and five real-world engineering optimisation problems show that the proposed strategy outperforms the basic ABC and recent variants of ABC, namely, Gbest-guided ABC, best-so-far ABC and modified ABC in most of the experiments.