Desai, Kaushal A

Nickel-Based Superalloys (NBSAs) are widely used for components subjected to high-temperature applications due to their excellent mechanical strength, toughness, and corrosion resistance. Despite favorable properties, NBSAs work-harden during machining, resulting in acute temperature rise at the cutting edge, severe plastic deformation, and rapid tool wear. The lower thermal conductivity, intense friction at the chip-tool interface, chemical affinity with tool material, and temperature gradients typically lead to abrupt crater formation or cutting-edge chipping in addition to rapid flank wear. Three distinct phenomena characterize tool wear during end milling of NBSAs; rapid flank wear, abrupt crater formation, and cutting-edge chipping. The continued use of worn or damaged cutting tools leads to poor surface finish and, eventually, catastrophic failures, resulting in significant machine downtime. As each tool wear condition has a unique mitigation strategy, timely identification and classification are imperative to implement solutions that minimize wear and guide tool replacement. In recent years, the augmentation of vision-based systems with pre-trained Convolutional Neural Networks (CNNs) has shown great promise in failure identification and classification tasks. The present work develops an image-based classification model using a pre-trained CNN, Efficient-Net-b3, for identifying three tool wear conditions during end milling of Inconel 718 (IN718). The network training uses labeled image datasets that capture various tool wear characteristics generated using end-milling experiments. The extensive training dataset requirement of the CNN was met using image augmentation techniques by varying the brightness, contrast, and orientation of the captured images. The prediction abilities of the algorithm were corroborated by validating the model on a validation dataset and further testing on new unseen datasets. It has been shown that Efficient-Net-b3 demonstrates robust prediction accuracy for all three tool wear conditions. The proposed classification model can be further employed for developing an on-machine vision-based tool wear classification system.

Mobile computing can effectively monitor tool life by establishing a relationship between periodically captured cutting tool images and the usefulness level of an end mill. This work presents an image-based deep-learning model to estimate end mill wear parameters and provide tool state feedback to the machine operator. The algorithm estimates the Remaining Useful Life (RUL) and tool wear state from the mobile camera images, viz. initial, intermediate, and worn. The operator captures cutting tool images at predefined intervals on the machine using a mobile camera, macro lens, and tripod arrangement. A pre-trained network, GoogLeNet, is employed for feature extraction, linear regression, and recognizing the tool wear status as RUL. A mobile application is developed to display the wear state and RUL for assisting machine operators in replacing/regrinding decisions. The accuracy and robustness of the proposed model are demonstrated using RMSE (Root Mean Square Error) and Correlation Coefficient (R2) metrics. A set of machining experiments are performed, and it has been shown that the developed module can capture wear states and RUL for end mills. The proposed solutions can be deployed effectively by manufacturing industries for obtaining tool wear information without significant investment in machine vision hardware and software.

This paper presents a comparative assessment of three different approaches to highlight the importance of incorporating bottom and flank cutting edges in cutting force models for flat-end milling operation. The study focuses on identifying the most appropriate method that includes the effect of both cutting edges and predicts accurately over a wide range of cutting widths, i.e., axial depth of cut (ADOC) and radial depth of cut (RDOC). The first approach uses the average cutting constants directly estimated from the experimental force data. The second approach pre-processes the experimental data to exclude the contribution of bottom edges and determine flank constants for the estimation of cutting forces. The third approach considers the systematic derivation of independent coefficients for flank and bottom cutting edges and summing the individual contribution to determine cutting force. These approaches are implemented in the form of computational models, and machining experiments are conducted to examine the efficacy of proposed methods in estimating cutting force for flat-end milling operation. Based on the outcomes of the study, it is realized that the third approach can predict cutting forces accurately over a wide range of cutting widths. Also, it is observed that the bottom edge has a marked effect on the normal force component for select combinations of cutting widths.

The advancements in the domain of CAD/CAM and CNC machine tools facilitated machining of complex geometric shapes to meet functional requirements and/or aesthetic appearances. These shapes combine several geometric features such as zero curvature (straight), constant curvature (circular) and variable curvature surfaces. The components often contain thin-walled sections having inherently lower stiffness that induces static deflections transforming into surface error and violation of error limits specified by the designer. This paper presents a comparison of deflection induced surface error profile generated during the end milling of zero and constant curvature thin-walled components. The proposed framework incorporates computational model to estimate cutting forces, Finite Element Analysis (FEA) model to compute workpiece deflections, and surface generation mechanism to derive error profile. The paper also investigates the effect of change in the radial engagement area due to workpiece curvature by introducing the concept of 'Equivalent Radial Depth of Cut'. Further, the effect of change in workpiece curvature is investigated on the surface error profile in the paper. The proposed framework has been generalized to accommodate the variation of workpiece geometry, and the results are validated by conducting a set of end milling experiments.

This paper presents the design, development and testing of a novel neck chamber device for non-invasive stimulation of an individual carotid baroreceptor in a graded manner. The proposed neck chamber device is a strap-free design that avoids discomfort during testing due to tight seal generated by the neck collar design, and facilitates unilateral testing and targeted assessment without stimulating other neck baroreceptors. The device consists of two independent components to achieve these requirements: an outer suction mechanism and an inner chamber. The outer mechanism consists of multiple suction cups to grip the device over the human neck, while the inner chamber creates controlled positive and negative pressure for stimulation of baroreceptors using a pump. The indigenously developed device was employed for the testing by providing neck chamber stimulation in discrete steps of -20 mm Hg, -40 mm Hg, -60 mm Hg, 0 mm Hg, 20 mm Hg, 40 mm Hg and 60 mm Hg with the gap of 60 s between each stimulation as per the standard test protocol of autonomic function test. The changes in heart rate and RR interval were recorded to determine the baroreceptor gain using the logistic equation derivative and gain curve plot. The results of the present study show that the estimated baroreceptor gain is -0.109±0.04, which is consistent with the previous studies conducted using neck collar devices. The testing results showed that the desired objectives are achieved successfully by the prototype device, opening up the possibility of its use for the treatment of resistant hypertension.

Monitoring twist drill chatter is essential to avoid catastrophic failures, achieve better hole accuracy, and realize smart manufacturing goals. This paper presents a framework for developing a supervisory system that combines a sensor, data acquisition, detection algorithm, and Human Machine Interface (HMI) to achieve chatter-free operation of manual drilling machines. It utilizes an accelerometer for capturing real-time process information and extracts features from the sensor data using Root Mean Square (RMS) and Quadratic Support Vector Machine (QSVM) algorithms. The drilling operation stability or chatter conditions are communicated to the operator through HMI for enhanced human-process interactions. The proposed supervisory system has been implemented on a manual drilling machine to achieve chatter-free operations and demonstrate robust performance under various conditions. The developed framework is validated by performing manual drilling experiments with typical work materials (Aluminum, Mild Steel, and Titanium) and drill (High-Speed Steel and Solid Carbide) combinations over a range of feed rates and spindle speeds.

The application of data-driven or machine learning models is becoming imperative in recent times to analyze manufacturing process attributes. These models use input and output datasets to evolve the relationship similar to human perceptions. The development of a reliable data-driven model is challenging due to the necessity of conducting numerous experiments, the presence of outliers and noise in the datasets, process disturbances, etc. The data-driven models can be scaled easily by accommodating new variables and attributes to evolve progressively. Alternatively, physics-based models establish an explicit relationship between process variables and desirable attributes based on scientific knowledge and a set of assumptions, but its scalability is difficult. This paper presents the development of a hybrid cutting force model for end milling operation, combining both approaches to ensure that adequate process knowledge is captured. The outcomes of the proposed method are substantiated by performing a set of computational studies and end milling experiments.

The identification of appropriate empirical relationships between cutting force coefficients and the uncut chip area is crucial for the successful implementation of mechanistic models in estimating cutting forces for flat-end milling operation. The derivation of empirical relationships necessitates machining experiments to record cutting force components under diverse conditions. The experimental data collected from force sensors (mainly dynamometers) contains outliers and noise that deteriorate the goodness of fit and thereby prediction accuracy of the model. This paper presents an application of the Gaussian approach to refine experimentally measured force data by systematically eliminating outliers and noise, followed by the use of pre-processed data to derive empirical relationships. The proposed methodology is implemented in the form of a computational tool to eliminate irrational data points automatically and obtain meaningful cutting force coefficients relationships using regression models. The outcomes of the study are substantiated further by conducting a set of experiments over a wide range of cutting conditions. The root mean square error (RMSE) of measured and predicted cutting forces is estimated for models with and without a data refining approach, which showed marked improvement in the prediction accuracy. Based on the outcomes of the present study, it can be concluded that the prediction ability of the mechanistic force model can be improved considerably with the augmentation of the Gaussian approach.

Micro-end milling is used for manufacturing of complex miniaturized components precisely in wide range of materials. It is important to predict cutting forces accurately as it plays vital role in controlling tool and workpiece deflections as well as tool wear and breakage. The present study attempts to incorporate process characteristics such as edge radius of cutting tool, effective rake and clearance angles, minimum chip thickness, and elastic recovery of work material collectively while predicting cutting forces using mechanistic model. To incorporate these process characteristics effectively, it is proposed to divide cutting zone into two regions: shearing- and ploughing-dominant regions. The methodology estimates cutting forces in each partitioned zone separately and then combines the same to obtain total cutting force at a given cutter rotation angle. The results of proposed model are validated by performing machining experiments over a wide range of cutting conditions. The paper also highlights the importance of incorporating elastic recovery of work material and effective rake and clearance angle while predicting cutting forces. It has been observed that the proposed methodology predicts the magnitude and profile of cutting forces accurately for micro-end milling operation.

The static deflections of the cutting tool and thin-walled components are key sources contributing to the deviation of a machined surface from the design specifications during the end milling operation. The machined surface deviation is expressed using geometric tolerances such as flatness and cylindricity parameters specified as per the Geometric Dimensioning and Tolerancing (GD&T) standard (ASME Y14.5-2009 or ISO 1101). The present work investigates the effect of component configuration, engagement area, and workpiece curvature by comparing geometric errors during the end milling of zero and constant curvature thin-walled components. An integrated computational framework incorporating the mechanistic force model, finite element (FE)-based workpiece deflection model, cantilever beam formulation-based tool deflection model, and particle swarm optimization (PSO)-based geometric tolerance estimation model has been adopted from the previous work of authors. The effect of component geometry and cutter-workpiece transition are investigated on the geometric tolerance (flatness and cylindricity) by conducting computational studies and machining experiments under identical cutting conditions. The concept of “Equivalent Radial Depth of Cut (RDOC)” is introduced to derive component configurations with the identical cutter-workpiece transition area. The influence of workpiece curvature on the geometric tolerance parameters is also investigated in the paper. The outcomes are substantiated by performing computational studies and machining experiments. It is recognized that the relatively enhanced stiffness of the curved components offers an inherent machining advantage in comparison to straight components to the process planners.