Neuro-controller implementation for the embedded control system for mini-greenhouse

Abstract

Control of a certain object can be implemented using different principles, namely, a certain software-implemented algorithm, fuzzy logic, neural networks, etc. In recent years, the use of neural networks for applications in control systems has become increasingly popular. However, their implementation in embedded systems requires taking into account their limitations in performance, memory, etc. In this article, a neuro-controller for the embedded control system is proposed, which enables the processing of input technological data. A structure for the neuro-controller is proposed, which is based on the modular principle. It ensures rapid improvement of the system during its development. The neuro-controller functioning algorithm and data processing model based on artificial neural networks are developed. The neuro-controller hardware is developed based on the STM32 microcontroller, sensors and actuators, which ensures a low cost of implementation. The artificial neural network is implemented in the form of a software module, which allows us to change the neuro-controller function quickly. As a usage example, we considered STM32-based implementation of the control system for an intelligent mini-greenhouse.