ANFIS modeling to predict the friction forces in CNC guideways and servomotor currents in the feed drive system to be employed in lubrication control system. (August 2017)

• Record Type: Journal Article
• Authors: Sparham, Mahdi; Sarhan, Ahmed A.D.; Mardi, N.A.; Hamdi, M.; Dahari, M.
• Is Part Of: Journal of manufacturing processes. Volume 28:Part 1(2017)
• Page Start: 168
• Page End: 185
• Publication Date: 2017-08
• Subjects: Adaptive neuro-fuzzy modeling -- CNC cutting parameter -- Friction force -- Cutting force -- Servomotor current; Production management -- Data processing -- Periodicals; Manufacturing processes -- Periodicals; Procestechnologie; Productietechniek; Production -- Gestion -- Informatique -- Périodiques; Fabrication -- Périodiques; Manufacturing processes; Production management -- Data processing; Periodicals; 670.5
• DOI: 10.1016/j.jmapro.2017.05.020
• Languages: English
• ISSNs: 1526-6125

Abstract

Graphical abstract: The optimum model structure of ANFI for friction force. Highlights: Current consumption of each feed servomotor was measured during a full cutting cycle. The friction force in linear guideways were calculated using cutting force analysis. ANFIS modeling was built to predict the friction force in CNC machines guideways. ANFIS modeling was built to predict servomotor current in the feed drive system. ANFIS models will be used to build the oil feedback lubrication control system. Abstract: In this research work, Adaptive Neuro-Fuzzy Inference System (ANFIS) modeling is implemented to predict the friction force in the CNC linear guideways and servomotor current in the feed drive system in dry lubrication condition. Initially, the friction forces in the CNC linear guideways are calculated from the cutting force analysis during cutting in dry lubrication condition. Second, the servomotor currents on the X and Z-axes are measured during cutting in the same condition. Finally, ANFIS modeling to predict the friction force in CNC linear guideways and servomotor current is established using the training data obtained from cutting. Furthermore, the ANFIS prediction error and accuracy for both friction force and servomotor currents are investigated. The results demonstrate that the proposed ANFIS model can predict friction forces and servomotor currents with 1.38% and 4.1% errors, respectively. The low error percentages indicate that ANFIS modeling can be employed in a new technique for a lubrication control system for green manufacturing.