This article explores various architectures of neural networks in order to create models in the field of agriculture, with an emphasis on their use in livestock farms. The paper describes the architecture of Kolmogorov-Arnold networks, considers the stages of data collection and preliminary preparation, the learning process of neural networks, as well as their implementation. As a result, models were developed using Kolmogorov-Arnold networks and a multilayer perceptron. The study compared the effectiveness of the proposed architectures. The experiment demonstrates that Kolmogorov-Arnold networks have higher accuracy in predictions, which makes them a promising tool for forecasting. The developed model has been integrated into the livestock information system being developed to predict the growth, health and other indicators of animals, allowing for more accurate management of the growing process.
Keywords: precision animal husbandry, Kolmogorov-Arnold network, modeling, neural network, monitoring, cultivation, data modeling, forecasting
This paper deals with the development of automatic control system for sausage smoking chamber. Manual control of the smoking process can lead to errors and irregularity, so automation becomes a necessity. Smoking chamber control system works on two circuits - temperature and humidity. An automatic smoking chamber control system provides optimum conditions for smoking products. The paper presents the transfer functions for each circuit and the structural diagram of the control system. The coefficients used in the calculations were obtained from experiments conducted at a sausage production facility in Izhevsk. The paper analyzes the stability of the system by calculations and verification in the Matlab Simulink environment. Based on the verification, it was found out that the automatic control system of the sausage smoking chamber developed by us is working.
Keywords: smoking chamber, control object, humidity control circuit, temperature control circuit, automatic control system