In the context of water scarcity and tightening environmental requirements, improving the energy efficiency of biological wastewater treatment processes has become particularly important. The aeration tank is one of the most energy-intensive and dynamically complex units, strongly affected by the variability in influent flow and composition. Conventional PID controllers do not provide predictive disturbance compensation and often result in excessive aeration and increased energy consumption. The study proposes an intelligent control approach based on a digital twin, neural network-based influent flow forecasting, and model predictive control (MPC). The digital twin represents a dynamic model of the biological process incorporating key state variables, including substrate, activated sludge, and dissolved oxygen concentrations. The LSTM neural network model is employed to predict the hydraulic load based on historical plant operation data, as well as to compensate for residual nonlinear dynamics that are not represented by the linearized MPC model. The predicted influent flow values are incorporated into the MPC framework as measured disturbances, enabling the generation of anticipatory control actions for the aeration system. The adequacy of the digital twin was validated using operational data from the wastewater treatment facilities of Semey city and was characterized by RMSE = 0.14 mg/L, MAE = 0.09 mg/L, R² = 0.94, and MAPE = 6.3%. The simulation results demonstrated that, compared with the fuzzy PID controller, the application of MPC reduced the RMSE by 57.1%, decreased the overshoot from 24% to 8%, reduced the integral absolute error (IAE) by 60.9%, and lowered the energy consumption of the aeration system by 21.1%, while maintaining the dissolved oxygen concentration within the permissible operating range. The proposed Advisory MPC architecture is compatible with existing PLC–SCADA systems and can serve as a basis for the gradual digital modernization of wastewater treatment facilities without modifying the existing automation loops.

The article considers SMART technology, in particular smart house and basic communication protocols used for data exchange. Smart house technology additionally bears the name «home automation». Home automation in modern conditions allows the user or consumer to flexibly manage and independently configure the system, depending on the requirements of the user. One of the stages of customization of smart home technology is the selection of communication protocol for data exchange within the smart home system.To implement data exchange in smart home technology, it is necessary to properly approach the choice of communication protocols. Smart home technology uses several types of devices: controllers, sensors, acoustics. Since not all devices support existing protocols, there are also unique devices that support several of the existing protocols. There are several protocols used in smart home technology: ZigBee, Z-Wave, Wi-Fi.In this article the analysis of two main wireless protocols operating at high frequencies, namely ZigBee and Z-Wave. Correctly selected protocols implement fast data transmission without loss. In addition, it will be possible to realize the needs of the user or user, which are set by the system.

The article presents the results of the development and research of a digital twin of a training manipulator with two joints 230 and 170 mm long and a working range of 170-400 mm. The aim of the work is to create a virtual model that allows the kinematic and functional behaviour of the real device to be adequately reproduced. Additionally, to evaluate its potential for use in the educational process. The methods used include mathematical modelling of direct kinematics, numerical analysis of the working area, and visualisation of the motion trajectory. The results showed that the root mean square positioning error of the digital twin does not exceed 3- 4 mm, which is less than 1% of the maximum working radius and confirms the high accuracy of the model. The working area of the manipulator, calculated using the random approximation method, fully corresponds to the passport limitations of the real device. The pedagogical experiment showed that the use of a digital twin significantly improves students' understanding of the principles of robotics and manipulator kinematics. The developed model can be used as an effective tool for conducting laboratory work, training specialists in the field of automation and robotic systems, as well as for subsequent expansion to include dynamic characteristics and automatic motion planning algorithms.

This article presents a study of algorithms using machine vision to control a robot manipulator. With the increasing number of robots used in industry and other industries, the need for reliable and accurate control algorithms has increased. Thus, the relevance of the topic increases, and research in this area can significantly improve the efficiency and safety of robotic systems. The purpose of this article is a comprehensive study of various control algorithms, as well as the integration of machine vision into control systems. Robot manipulator control algorithms are a set of mathematical procedures and methods that allow robots to perform certain movements and tasks with the necessary efficiency and accuracy. To do this, the robot receives important data about the world around it using machine vision. The article considers three main types of algorithms: inverse kinematics, PID controllers and machine learning algorithms. Reverse kinematics determines the angles of rotation of the robot joints, which are necessary to achieve a given position and orientation of the working tool. The PID controller controls the movements of the robot's joints. By controlling the speed and force, it corrects errors between the actual and the set position. Using machine learning methods allows you to learn new tasks and adapt your behavior to changing conditions. Within the framework of this study, the theoretical aspects of algorithms and machine vision will be considered. The research was carried out on the Optima 2 manipulator manufactured by ZARNITZA.

The article considers SMART technology, in particular smart house and basic communication protocols used for data exchange. Smart house technology additionally bears the name «home automation». Home automation in modern conditions allows the user or consumer to flexibly manage and independently configure the system, depending on the requirements of the user. One of the stages of customization of smart home technology is the selection of communication protocol for data exchange within the smart home system.To implement data exchange in smart home technology, it is necessary to properly approach the choice of communication protocols. Smart home technology uses several types of devices: controllers, sensors, acoustics. Since not all devices support existing protocols, there are also unique devices that support several of the existing protocols. There are several protocols used in smart home technology: ZigBee, Z-Wave, Wi-Fi.In this article the analysis of two main wireless protocols operating at high frequencies, namely ZigBee and Z-Wave. Correctly selected protocols implement fast data transmission without loss. In addition, it will be possible to realize the needs of the user or user, which are set by the system.

The purpose of the research in this article is to improve the operation of urban water treatment plants using biological purification using neural network technologies. Before controlling aeration in the aeration tank, the neural network processes the volume of incoming wastewater (flow and level sensors measure the volume of incoming wastewater, flow rate and its dynamics. Dissolved oxygen sensors monitor the oxygen level in the aeration tank, which is critical for the work of microorganisms, for example, if an increase in water volume is predicted, the system increases the oxygen supply in advance. The constant collection of data from sensors allows you to compare the actual parameters with the predicted ones, correcting the operation of the system in real time. The integration of predictive analytics with aerotank control systems allows for a synergistic effect: 1 – Forecasting the parameters of incoming wastewater provides an opportunity to adjust the system operation in advance, 2 – Adaptive control of aeration and activated sludge reduces energy consumption and increases the efficiency of biological treatment. Continuous monitoring and feedback will allow the system to dynamically respond to changes, ensuring process stability and preventing emergencies. Thus, neural network algorithms, combined with SCADA systems, form the basis for intelligent automation of wastewater treatment plants, which contributes not only to improving the quality of wastewater treatment, but also to significant savings in energy resources, reducing operating costs and improving environmental safety.