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.

Adaptive business process management for small and medium enterprises combining machine learning, serverless orchestration, and NIST-based cybersecurity to handle concept drift efficiently and securely.

This paper deals with the automation of biological water treatment system using fuzzy logic. The main objective of the work is to develop a fuzzy controller capable of adapting to the changing conditions of the purification process. The implementation of fuzzy logic can improve the control efficiency by considering many factors affecting the purification process. The paper proposes fuzzy control rules for optimising the operation of pumps, aeration systems and reagent supply, as well as methods for their implementation.Methodology: The methodology includes analysis of existing cleaning methods, development of a fuzzy control system, its modelling and experimental validation. First, current technologies and their potential for automation are investigated. Then fuzzy control rules are developed based on expert data and mathematical models. Next, the system is modelled to verify the performance and at the end it is experimentally tested on laboratory or production units.Main results: An automated control system for biological water treatment based on fuzzy logic has been developed to adapt to changes in environmental parameters. Modelling of the system operation confirmed its ability to properly regulate the operation of pumps, aeration systems and reagent supply. Experimental studies have shown that the use of fuzzy logic helps to increase the stability of the purification process.

The compilation of optimal production plans often requires consideration of the fuzziness in certain initial information. Therefore, a pertinent issue in the theory and practice is the solution of production plan optimization problems under conditions of fuzzy information using mathematical models and tools of fuzzy sets. The research aims to develop various formulations for optimization problems of production plans using the example of a feed production plan. The problem is addressed based on a modified model considering fuzzy constraints by adapting various optimality principles. The research focuses on the processes of feed mixture production at the Makinsk poultry farm, characterized by fuzzy constraints on feed composition. New formulations of optimization problems under fuzzy constraints are obtained in the form of fuzzy mathematical programming problems, and heuristic methods for their solution are proposed. Various scenarios are considered, where the original multi-criteria optimization problem can be reduced to a single-criterion problem. For each formulation of the optimization problem, modifications of Pareto optimality methods and the main criterion are applied, ensuring the effective utilization of expert information and the decision maker’s knowledge during the optimization process and the selection of the best solution.

The article discusses a three-circuit cascade system for automatic control of the water level in a steam boiler using adaptive adjustment of the coefficients of the PID controller. A feature of the proposed system is the use of fuzzy logic for adaptive correction of regulator parameters, which ensures stable and reliable operation of thermal power equipment under various external and internal disturbances. The developed control structure includes three interconnected circuits: water level control through feed water flow, steam flow control, and steam flow control through fuel supply. The use of second-order models, taking into account thermophysical characteristics, makes it possible to increase control accuracy and reduce energy losses. The adaptive adjustment system provides automatic adjustment of the coefficients of the PID controller depending on the current state of the control object. It is shown that the adaptive system effectively compensates for unsteady fluctuations in the water level caused by the characteristics of a two-phase medium and transient conditions, increasing the reliability and stability of the thermal engineering process. The results of numerical modeling and analysis confirm the effectiveness of the proposed approach in conditions of changing object characteristics, noise, delays, and limited information about environmental parameters, which is especially important for complex multiconnected systems.