A Novel Computer Vision Based Machine Learning Approach For Online Tool Wear Monitoring In Machining

With the increased scope of automated machining processes, one of the essential requirements is the reliable predictions of the tool life. It is crucial to monitor the condition of the cutting tool during the machining process to achieve high-quality machining and cost-effective production. This paper presents a computer vision technique for flank wear measurement and prediction using machine learning, specifically support vector machine (SVM) and boosted decision trees has been used. The proposed methodology for tool wear measurement is illustrated for the CNC machining experimentally. The direct method of tool wear measurement and prediction have been proposed. Flank wear measurement is carried out on PVD coated tool insert, and experiments are performed on an alloy steel workpiece under dry machining. For capturing images, a CMOS camera with a lens mounted on the machine is used. To avoid environmental effects on the images LED ring light is used. Captured tool insert images are provided to the image processing algorithm built-in MATLAB software. The measurement of flank wear is also carried out using a microscope. The prediction accuracy of SVM and optimized boosted tree models is 97% and 96%, respectively, proving prediction algorithms' effectiveness. The findings showcased that the proposed methodology can measure and predict the tool wear with higher accuracy. It has demonstrated the ability to increase cutting tool utilization with the improved surface finish of the machined component.

Characterization and Parametric Optimization of Performance Parameters of DLC-Coated Tungsten Carbide (WC) Tool Using TOPSIS

In this work, we have deposited the diamond-like carbon (DLC) coating on the tungsten carbide (WC) tool insert using the thermal chemical vapor deposition (CVD) method. For the growth of DLC coating, sugarcane bagasse was used as a carbon precursor. Raman spectroscopy, a field emission scanning electron microscope (FESEM), and X-ray diffraction (XRD) were used to confirm the presence of DLC coating on the tungsten carbide tool inserts. The hardness tests were also performed for inspecting the microhardness induced by the self-developed DLC coating on the tungsten carbide (WC) tool insert. To determine the optimum process parameters for the turning operation on an aluminum (6061) workpiece using a self-developed DLC-coated tungsten carbide (WC) tool insert, we have applied the technique for order preference by similarity to ideal solution (TOPSIS) methods. The process parameters considered for the optimization were feed rate, cutting speed, and depth of cut. Whereas chosen response variables were flank wear, temperature in the cutting zone, and surface roughness. TOPSIS is utilized to analyze the effects of selected input parameters on the selected output parameters. This study in this paper revealed that it was advantageous to develop the DLC coating on the tungsten carbide tool inserts for the machining applications. The results also revealed that a 0.635 mm depth of cut, feed rate of 0.2 mm/rev, and cutting speed of 480 m/min were the optimum combination of process parameters.

Selective laser melting for improving quality characteristics of a prism shaped topology injection mould tool insert for the automotive industry

Manufacturing process constraints and design complexities are the main challenges that face the aftermarket automotive industry. For that reason, recently, selective laser melting (SLM) is being recognised as a viable approach in the fabrication of injection moulding tool inserts. Due to its versatility, SLM technology is capable of producing freeform designs. For the first reported time, in this study SLM is recognized for its novel application in overcoming fabrication complexities for prism shaped topology of a vehicle headlamp’s reflector injection moulding tool insert. Henceforth, performance measures of the SLM-fabricated injection mould tool insert is assessed in comparison to a CNC-milled counterpart to improve quality characteristics. Tests executed and detailed in this paper are divided into two stages; the first stage assesses both fabricated tool inserts in terms of manufacturability; the second stage assesses the functionality of the end-products by measuring the surface roughness, dimensional accuracy and light reflectivity from the vehicle reflectors. The results obtained show that employing SLM technology can offer an effective and efficient alternative to subtractive manufacturing, successfully producing tool inserts with complex surface topology. Significant benefits in terms of surface roughness, dimensional accuracy and product functionality were achieved through the use of SLM technology. it was concluded that the SLM-fabricated inserts products proved to have relatively lower values of surface roughness in comparison to their CNC counterparts.