The models for forecasting time series with seasonal variability can be used to build automatic real-time control systems. For example, predicting the water flowing in a wastewater treatment plant can be used to calculate the optimal electricity consumption. The article describes a performance analysis of various machine learning methods (SARIMA, Holt-Winters Exponential Smoothing, ETS, Facebook Prophet, XGBoost, and Long Short-Term Memory) and data-preprocessing algorithms implemented in Python. The general methodology of model building and the requirements of the input data sets are described. All models use actual data from sensors of the monitoring system. The novelty of this work is in an approach that allows using limited history data sets to obtain predictions with reasonable accuracy. The implemented algorithms made it possible to achieve an R-Squared accuracy of more than 0.95. The forecasting calculation time is minimized, which can be used to run the algorithm in real-time control and embedded systems.

The article is devoted to the consideration of the issue of building intelligent control of manipulators of an anthropomorphic robot. The paper considers the approach of transmitting data when building management through training with a teacher using a copying suit. The structure of the knowledge base for building management has been considered. The proposed approach is an effective alternative to building control through solving complex systems of differential and finite-difference equations of a high order, which do not always take into account all the features of the functioning of manipulators in various environments.

The article deals with the technology of vector machines for solving prediction and classification problems. The specialized software that used LibSVMsharp library is represented.

The purpose of the paper is to investigate the approach to the Unmanned Aerial Vehicle (UAV) control system synthesis, based on linear-quadratic optimization methods. The paper considers the challenges of developing an optimal control system for UAV “dry” landing (without landing on a sea surface) on a non-aircraft carrier vessel. The purpose of the control system is to guide the UAV to the centerline of the landing strip. To achieve it, lateral movement commands are sent separately through the yaw control loop. In this case, the decoupling of the roll and yaw control loops is obtained as a result of structuring the control system. In this paper the structuring is carried out by transforming the structural diagrams of the UAV control system where the initial motion model of the UAV is non-linear. As a result, the linearization of this non-linear model is performed first. Then, the linearized model is represented in the complex domain in the form of a structural diagram with the corresponding transfer functions. The design of optimal lateral motion control of the UAV is carried out by using the linear-quadratic optimization method in the complex domain. Optimization is carried out separately for the yaw control loop (inner loop) and the lateral movement control loop (outer loop). A quadratic criterion in the form of restrictions on the control energy is used as an optimization criterion. The authors provide examples of system modeling in the article. Copyright © 2020 Praise Worthy Prize - All rights reserved.

Control of airflow of activated sludge systems has significant challenges due to the non-linearity of the control element (butterfly valve). To overcome this challenge, some valve manufacturers developed valves with linear characteristics. However, these valves are 10–100 times more expensive than butterfly valves. By developing models for butterfly valves installed characteristics and utilizing these models for real-time airflow control, the authors of this paper aimed to achieve the same accuracy of control using butterfly valves as achieved using valves with linear characteristics. Several approaches were tested to model the installed valve’s characteristics, such as a formal mathematical model utilizing Simscape/Matlab software, a semi-empirical model, and several machine learning methods (MLM), including regression, support vector machine, Gaussian process, decision tree, and deep learning. Several versions of the airflow-valve position models were developed using each machine learning method listed above. The one with the smallest forecast error was selected for field testing at the $55.5\times {10}^3 {\mathrm{m}}^3/\mathrm{day} \left(12 \mathrm{MGD}\right)$ City of Chico activated sludge system. Field testing of the formal mathematical model, semi-empirical model, and the regularized gradient boosting machine model (the best among MLMs) showed that the regularized gradient boosting machine model (RGBMM) provided the best accuracy. The use of the RGBMMs in airflow control loops since 2019 at the City of Chico wastewater treatment plant showed that these models are robust and accurate (2.9% median error).