Nowadays, great emphasis is placed on minimizing energy consumption, and this also applies to material processing. To minimize grinding energy, it is necessary to have a model representing the dependence of grinding energy on various parameters. The article presents preliminary results of work on creating an expert system in the form of an artificial neural network modeling the dependence of grinding energy on grinding depth. Searching for new modeling solutions will allow for achieving new solutions for micro- and nano-grinding in the future. Predicting the results of grinding force components will allow for determining the work required to remove a micro- and nanolayer.NEURAL MODEL OF ENERGY DETERMINATION DURING PERIPHERAL GRINDING PROCESS OF ENGINE PARTS
Nowadays, a lot of pressure is put on minimizing energy consumption in all areas of our lives, this also applies to materials processing. To minimize the energy of grinding, you must have a model that represents the grinding energy depending on various parameters. The article presents the preliminary results of work on the establishment of the expert system in the form of an artificial neural network modeling input energy dependence on the depth of grinding. Disadvantages of conventional methods of grinding (high energy related to the unit and the machined surface due to the effects of) restricts the use of conventional methods in micro-and nano-grinding. Searching for a new ways in modeling allows to develop the new methods of nano-grinding. Based on predicted results will make possible determination of energy required to remove microand nanolayers. (…)
The article contains 13668 characters.
Source: Logistyka Magazine