Novel Approach to Monitoring the Surface Integrity of Aluminum 5052 Using Sound and Vibration Signals during Turning with Titanium-Coated Carbide Inserts

This study presents a novel approach for online monitoring of surface roughness in the context of Industry 4.0. Aluminum 5052 is machined, and the sound emitted is captured with a studio condenser microphone and processed in FL Studio sound software. Fast Fourier transform deconvolution is employed to visualize the noise scale in the span master plugin. It is observed that the noise signal can be cast off to detect tool condition and surface roughness with an improvement of up to 30% compared to traditional methods. Furthermore, Taguchi analysis is employed to compare the TiN-coated and uncoated silicon carbide inserts while turning Aluminum 5052. The literature gap in this research pertains to the absence of comparative analysis with more advanced coatings like TiAlN, potentially overlooking superior options for enhancing machining efficiency and surface integrity (SI) in aluminum alloys. The TiN coating is found to provide better lubrication and results in lower vibration, noise, and surface roughness with an improvement of up to 20%. Lastly, a synergistic effect between feed rate and machining speed is observed on the noise signal as well as on the SF. Taguchi optimization can be used to identify the process parameters that have the greatest influence on the SI of aluminum 5052 during turning with titanium-coated carbide inserts. This research uses the Taguchi method to determine optimal settings of machining parameters to maximize the SI of the material. The optimum condition for a high material removal rate and a high-quality surface is established as 750 rpm, cutting depth 1 mm, and feed rate 0.16 mm/rev. Thus, this work proposes an effective and reliable method for online monitoring of surface roughness using noise amplitude during machining suitable for modern industries.