Artificial Intelligence Fuzzy Logic Modeling of Surface Roughness in Plasma Jet Cutting Process of Shipbuilding Aluminium Alloy 5083
Journal Title: Journal of Materials and Engineering - Year 2023, Vol 1, Issue 2
Abstract
In this paper the influence of different process parameters on surface roughness responses in plasma jet cutting process was investigated. Experimentations were conducted on shipbuilding aluminium 5083 sheet thickness 8 mm. Experimental work was performed according to Taguchi L27 orthogonal array by varying four parameters such as gas pressure, cutting speed, arc current and cutting height. Due to complexity of manufacturing process and aim to cover wide experimental space few constraints regarding cutting area were defined. Surface roughness parameters Ra and Rz were analysed as cut quality responses. In order to define mathematical model that will be able to describe effects of process parameters on surface roughness artificial intelligence (AI) fuzzy logic (FL) technique was applied. After functional relations between input parameters and surface roughness responses were defined prediction accuracy of developed fuzzy logic model was checked by comparison between experimental and predicted data. Mean absolute percentage error (MAPE) as well as coefficient of determination (R2) were used as validation measures. Finally, optimal process conditions that lead to minimal surface roughness were defined by creating response surface plots.
Authors and Affiliations
Ivan Peko, Bogdan Nedić, Dejan Marić, Dragan Džunić, Tomislav Šolić, Mario Dragičević, Boris Crnokić, Matej Kljajo
Keywords
Related Articles
- EP ID EP727412
- DOI 10.61552/JME.2023.02.005
- Views 72
- Downloads 0
Tribological Behaviour and Surface Roughness Quality of 3D Printed ABS Material
Additive manufacturing or 3D printing is one of the newer methods of manufacturing. The basic difference to other types of production is that the material is added in the form of layers. There are many types of technolog...
Triboinformatic Modeling of Wear in Total Knee Replacement Implants Using Machine Learning Algorithms
Pin-on-disk (PoD) tests, the most prevalent studies, are being carried out in order to evaluate tribological behaviour of different bearing materials. However, the comparison of results obtained from the PoD tests is ver...
Development and Tribological Analysis of Bio-Based Lubricant Using Two Non-Edible Oils: Castor Oil and Neem Oil
Lubricants play a very important role in multiple industries in minimizing wear and friction between two moving parts. Most lubricants are produced from petroleum oil which is poorly biodegradable and toxic in nature. He...
Effects of Applied Loads and Aluminium Nanoparticle Additions on Wear Resistance Properties of Particle Reinforced Epoxy Nanocomposites
The recent technology advancement has emerged aluminium nanoparticles for polymer reinforcements. Mechanical properties of epoxy containing aluminium nanoparticle was reported but its wear resistance is left unstudied. T...
Taguchi and Regression Analysis of Abrasive Wear Behavior of Carbon Epoxy Composite
This study aimed to assess the abrasive wear performance of a composite material made of carbon epoxy and graphite particles. The experiments were conducted on Abrasion Test rig and examined the weight loss of the compos...