Experimental investigation of cylinder liners and performance optimization using ANN

Area of Science:

• Materials Science
• Mechanical Engineering
• Computational Fluid Dynamics

Background:

• Cylinder liners in internal combustion engines are critical components requiring high structural integrity and optimized performance.
• Material selection and understanding thermomechanical stress response are key to enhancing engine efficiency and durability.

Purpose of the Study:

• To investigate the structural integrity and performance optimization of cylinder liners.
• To evaluate cast iron, nickel-chromium iron alloy, and aluminum alloy under engine conditions.
• To utilize Artificial Neural Networks (ANNs) for optimizing performance parameters.

Main Methods:

• Finite Element Analysis (FEA) to assess thermomechanical stresses, wear, and heat dissipation.
• Experimental assessment of material properties.
• ANNs for predicting material behavior under varying thermal and load conditions.

Main Results:

• Nickel-Chromium iron alloy demonstrated the lowest combined stress, indicating superior thermal stress resistance.
• Cast iron showed excessive thermal-induced stress, while aluminum alloy experienced deformation due to thermal expansion.
• ANN-based optimization successfully reduced stress values by up to 20%.

Conclusions:

• Nickel-Chromium iron alloy is the most suitable material for cylinder liners due to its stress resistance.
• ANN optimization is a viable tool for material selection, predictive maintenance, and improving cylinder liner performance.
• Combined computational and experimental approaches enable optimized engine component design for enhanced strength and performance.