Application of artificial neuronal networks in modelling and prediction of filter damage in the industry of water manufacture
2004
Lazarevic, I. | Miljkovic, Z. | Bajovic, P. (Masinski fakultet, Beograd (Serbia and Montenegro). Katedra za proizvodno masinstvo)
This paper aims to show the realization of the system based on the artificial neural networks application in the process of monitoring of water filtration procedure, early predition of filter damage and initial activation of selfcleaning which is necessary to carry out so that the system would function properly. The most important characteristic of the filter is the change of differential pressure in the function of the water flow, and as this is a non-linear function, the choice of such supervising system and control process is justified. Considering the fact that the system permanently does the acquisition of information about the system state, it is possible, by using data about "rainy days", to define correlation between the characteristic of filter operation and outword atmosphere factor.
显示更多 [+] 显示较少 [-]