Study of Cutting Tool Condition Monitoring System for Turning Operation

Abstract

Tool Condition Monitoring (TCM) frameworks stand as significant advancements in upgrading machining effectiveness. In spite of a plenty of accessible TCM arrangements, their restricted reception in businesses, especially little and medium-sized ventures (SMEs), comes from difficulties, for example, obtrusive sensor necessities, time-escalated sending processes, and a lack of easy to understand, versatile arrangements rising up out of lab settings. The ongoing movement toward Industry 4.0 has prodded the interest for TCM arrangements in light of Web of Things (IoT) stages, described by fitting and-play abilities, quick organization, and negligible disturbance during arrangement, all with decreased dependence on broad trial testing. This paper presents an original TCM framework established on minimal expense, harmless sensors working as fitting and-play gadgets, an IoT stage working with quick organization, and a versatile application for continuous administrator criticism. The framework engineering incorporates an Arduino Uno Wi-Fi detecting hub, filling in as an edge-registering unit to determine a likeness record for device wear characterization; an AI hub using a Beagle Bone Slate to develop the AI model through a Python script; what's more, an IoT stage going about as the correspondence framework, enrolling all information for future examination. Trial approval on a CNC machine shows the viability of a calculated relapse model on the AI hub, offering a prudent and direct arrangement with a 88% exactness in device wear grouping. The whole arrangement causes an expense of EUR 170, requiring a couple of hours for organization. This approach holds critical interest for SME experts, conveying brief outcomes and obliging the combination of additional modern investigations, all while utilizing administrator input from the portable application during progressing creation.