This article presents the hardware and software implementation of an automated information system for biological wastewater treatment. It assesses pollution concentration distribution, considering variations in technical parameters related to biomass activity and the effects of technical subsystem malfunctions on biochemical processes, enabling detailed prediction and automation of wastewater treatment. A laboratory apparatus for analyzing iron-containing coagulant using photocalorimetry was developed, comprising an opaque flow cuvette for constant liquid flow and an information processing and storage unit. The experimental setup employs a Raspberry Pi 4 microcomputer in conjunction with a TCS230 color sensor to perform real-time analysis of color and light intensity. The sensor detects parameters like R, G, B, which are then converted into the HSL color space using an artificial neural network to determine the concentration of the useful element ( \(Fe^{3+}\) ). The developed software for determining iron concentration in the coagulant utilizes artificial intelligence and is implemented as a web application. It displays the coagulant’s color parameters, the determined iron concentration, and saves the measurement history in a database. The described system tackles a key challenge in wastewater treatment - the need for efficient monitoring and control of biochemical processes and technical parameters. Traditional methods often lack real-time monitoring and comprehensive analysis, leading to inefficiencies and potential environmental risks. In summary, the described hardware and software implementations address critical challenges in wastewater treatment by offering enhanced monitoring, automation, and control. Providing real-time insights and reducing manual intervention, these advancements contribute to more efficient and environmentally sustainable treatment processes.