No abstract

No abstract

Among the most widespread systems in industrial plants are automated drive systems, the key and most common element of which is the induction motor. In view of challenging operating conditions of equipment, the task of fault detection based on the analysis of electrical parameters is relevant. The authors propose the identification of patterns characterizing the occurrence and development of the bearing defect by the singular analysis method as applied to the stator current signature. As a result of the decomposition, the time series of the three-phase current are represented by singular triples ordered by decreasing contribution, which are reconstructed into the form of time series for subsequent analysis using a Hankelization of matrices. Experimental studies with bearing damage imitation made it possible to establish the relationship between the changes in the contribution of the reconstructed time series and the presence of different levels of bearing defects. By using the contribution level and tracking the movement of the specific time series, it became possible to observe both the appearance of new components in the current signal and the changes in the contribution of the components corresponding to the defect to the overall structure. The authors verified the clustering results based on a visual assessment of the component matrices’ structure similarity using scattergrams and hierarchical clustering. The reconstruction of the time series from the results of the component grouping allows the use of these components for the subsequent prediction of faults development in electric motors.

The paper presents a hybrid approach for short-term river flood forecasting. It is based on multi-modal data fusion from different sources (weather stations, water height sensors, remote sensing data). To improve the forecasting efficiency, the machine learning methods and the Snowmelt-Runoff physical model are combined in a composite modeling pipeline using automated machine learning techniques. The novelty of the study is based on the application of automated machine learning to identify the individual blocks of a composite pipeline without involving an expert. It makes it possible to adapt the approach to various river basins and different types of floods. Lena River basin was used as a case study since its modeling during spring high water is complicated by the high probability of ice-jam flooding events. Experimental comparison with the existing methods confirms that the proposed approach reduces the error at each analyzed level gauging station. The value of Nash–Sutcliffe model efficiency coefficient for the ten stations chosen for comparison is 0.80. The other approaches based on statistical and physical models could not surpass the threshold of 0.74. Validation for a high-water period also confirms that a composite pipeline designed using automated machine learning is much more efficient than stand-alone models.

In this paper, a multi-objective approach for the design of composite data-driven mathematical models is proposed. It allows automating the identification of graph-based heterogeneous pipelines that consist of different blocks: machine learning models, data preprocessing blocks, etc. The implemented approach is based on a parameter-free genetic algorithm (GA) for model design called GPComp@Free. It is developed to be part of automated machine learning solutions and to increase the efficiency of the modeling pipeline automation. A set of experiments was conducted to verify the correctness and efficiency of the proposed approach and substantiate the selected solutions. The experimental results confirm that a multi-objective approach to the model design allows achieving better diversity and quality of obtained models. The implemented approach is available as a part of the open-source AutoML framework FEDOT.