Search

This research presents a novel approach to fault diagnosis for CNC hobbing cutters using machine learning techniques, leveraging three-axis vibration data to ensure machining precision and tool reliability. Traditional methods of tool monitoring are insufficient for real-time and complex machining environments, prompting the integration of automated machine learning models. A robust dataset was collected from a CNC hobbing machine, capturing vibration signals under healthy and faulty tool conditions. Statistical features, including Root Mean Square (RMS), Crest Factor, and Kurtosis, were extracted from the vibration data for model training. Various machine learning algorithms, including Decision Trees, Efficient Linear models, Neural Networks, and Ensemble methods, were evaluated for their classification accuracy. Among these, the Ensemble model achieved perfect classification accuracy (100 %) with minimal computational cost, making it optimal for real-time applications. Explainable AI techniques, such as LIME and Shapley values, were employed to interpret model predictions, enhancing the system's transparency and reliability. The proposed framework demonstrated superior performance compared to existing methodologies in the literature, addressing key gaps such as overfitting, data quality, and model explainability. Real-world deployment challenges, including diverse operating conditions and generalizability across machines, were also discussed, with recommendations for incorporating multi-sensor data and transfer learning approaches in future research. This study establishes a foundation for predictive maintenance in CNC machining, significantly reducing downtime and improving operational efficiency through precise fault diagnosis in hobbing cutters.

IntroductionAdditive manufacturing (AM) is a revolutionary technology transforming traditional production processes by providing exceptional mechanical characteristics.MethodsThe present study aims explicitly to predict the hardness of Polycarbonate (PC) parts produced using AM. The objectives of this study are: (1) To investigate the process parameters that impact the ability to estimate the hardness of PC materials accurately, and (2) To develop a best-performing ML model from a range of models that can reliably predict the hardness of additively manufactured PC parts. Initially, fused filament fabrication (FFF), the most affordable AM technique, was used for the manufacturing of parts. Four process parameters, infill density, print direction, raster angle, and layer thickness, are selected for investigation. A heatmap is generated to obtain the influence of process parameters on hardness. Then, machine learning (ML) techniques create a range of predictive models that can predict hardness value considering the level of process parameters.ResultsThe developed ML models include Linear Regression, Decision Tree, Random Forest, K-nearest neighbor, Support Vector Regression, AdaBoost, and Artificial Neural Network. Further, an investigation has been done that includes choosing and improving ML algorithms and assessing the models’ performance.DiscussionPrediction plots, residual plots, and evaluation metrics plots are prepared to gauge the performance of the developed models. Thus, the research enhances AM capabilities by applying predictive modeling to process parameters and improving the quality and reliability of fabricated components.

This article details the existing wearable assistive devices that could mimic a human’s active range of motion and aid individuals in recovering from stroke. The survey has identified several risk factors associated with musculoskeletal pain, including physical factors such as engaging in high-intensity exercises, experiencing trauma, aging, dizziness, accidents, and damage from the regular wear and tear of daily activities. These physical risk factors impact vital body parts such as the cervical spine, spinal cord, ankle, elbow, and others, leading to dysfunction, a decrease in the range of motion, and diminished coordination ability, and also influencing the ability to perform the activities of daily living (ADL), such as speaking, breathing and other neurological responses. An individual with these musculoskeletal disorders requires therapies to regain and restore the natural movement. These therapies require an experienced physician to treat the patient, which makes the process expensive and unreliable because the physician might not repeat the same procedure accurately due to fatigue. These reasons motivated researchers to develop and control robotics-based wearable assistive devices for various musculoskeletal disorders, with economical and accessible solutions to aid, mimic, and reinstate the natural active range of motion. Recently, advancements in wearable sensor technologies have been explored in healthcare by integrating machine-learning (ML) and artificial intelligence (AI) techniques to analyze the data and predict the required setting for the user. This review provides a comprehensive discussion on the importance of personalized wearable devices in pre- and post-clinical settings and aids in the recovery process.

This study was designed to examine the effects of a trimethylolpropane trioleate (TMPTO)-based lubricant on thrust force and torque under the high-speed drilling of Al-6061 as an effective environmentally friendly cutting fluid. The tribological performance of three lubricant blends was evaluated based on ASTM standards. TMPTO base oil, notably enhances load-carrying capacity under extreme pressure conditions, with a seizer load of 7848 N. The best-performing oil was further optimized using a Taguchi-based design experiment to investigate the effect of different additive concentrations on thrust force and torque under actual contact conditions. Experiments were conducted using three critical machining parameters: additive concentration, spindle speed, and feed rate. The results of the ANOVA analysis reveal that spindle speed contributes most substantially (62.99%) to torque, with feed rate (23.72%) and additive concentration (7.74%) also showing significant impacts. On the other hand, thrust force is primarily influenced by feed rate (73.52%), followed by spindle speed (16.82%), and additive concentration (6.28%). Furthermore, a machine learning model was developed to predict and compare a few significant aspects of high-speed drilling machinability, including thrust force and torque. Three different error metrics were utilized in order to assess the performance of the predicted values, namely the coefficient of determination (R2), mean absolute percentage error (MAPE) and mean square error (MSE), which are all based on the coefficient of determination. Compared to other models, decision tree produces more accurate prediction values for cutting forces. The present study provides a novel approach for evaluating the most promising biodegradable lube oils and predicting cutting forces by formulating a perfect blend.

This study aimed to investigate the impact of a lubricant derived from trimethylolpropane trioleate on power consumption and surface roughness during high-speed drilling of Al-6061, with the goal of developing an environmentally friendly cutting fluid. The study investigated the impact of additive concentration, spindle speed, and feed rate on energy consumption and surface roughness using a Taguchi L27 orthogonal array. Through analysis of the Taguchi experimental outcomes and single-to-noise ratios, the parameters were ranked accordingly. The results of the ANOVA analysis reveal that spindle speed has the greatest impact on Power (87.89%), followed by followed feed rate (6.96%) and additive concentration (2.98%). However, feed rate (43.51%) has the most significant influence on surface roughness, followed by speed (38.48%) and additive concentration (11.90%). Varying additive concentration affects more on surface quality rather than power consumption. Furthermore, a machine learning algorithm was developed to forecast and compare various key aspects of high-speed drilling machinability, including power and surface roughness. Three different measures of accuracy were used to evaluate the performance of the projected values: coefficient of determination (R2), mean absolute percentage error, and mean square error. The decision tree performed better than other models in accurately predicting power and surface roughness. This research introduces an innovative method for assessing the most effective biodegradable cutting fluid and forecasting power and surface quality by developing an optimal combination. [ABSTRACT FROM AUTHOR]

In this study, we investigate the application of supervised machine learning algorithms for estimating the Ultimate Tensile Strength (UTS) of Polylactic Acid (PLA) specimens fabricated using the Fused Deposition Modeling (FDM) process. 31 PLA specimens were prepared, with Infill Percentage, Layer Height, Print Speed, and Extrusion Temperature serving as input parameters. The primary objective was to assess the accuracy and effectiveness of four distinct supervised classification algorithms, namely Logistic Classification, Gradient Boosting Classification, Decision Tree, and K-Nearest Neighbor, in predicting the UTS of the specimens. The results revealed that while the Decision Tree and K-Nearest Neighbor algorithms achieved an F1 score of 0.71, the KNN algorithm exhibited a higher Area Under the Curve (AUC) score of 0.79, outperforming the other algorithms. The findings offer valuable insights into the potential use of machine learning techniques in improving the performance and accuracy of predictive models in additive manufacturing. [ABSTRACT FROM AUTHOR]

Introduction: Additive manufacturing (AM) is a revolutionary technology transforming traditional production processes by providing exceptional mechanical characteristics. Methods: The present study aims explicitly to predict the hardness of Polycarbonate (PC) parts produced using AM. The objectives of this study are: (1) To investigate the process parameters that impact the ability to estimate the hardness of PC materials accurately, and (2) To develop a best-performing ML model from a range of models that can reliably predict the hardness of additively manufactured PC parts. Initially, fused filament fabrication (FFF), the most affordable AM technique, was used for the manufacturing of parts. Four process parameters, infill density, print direction, raster angle, and layer thickness, are selected for investigation. A heatmap is generated to obtain the influence of process parameters on hardness. Then, machine learning (ML) techniques create a range of predictive models that can predict hardness value considering the level of process parameters. Results: The developed ML models include Linear Regression, Decision Tree, Random Forest, K-nearest neighbor, Support Vector Regression, AdaBoost, and Artificial Neural Network. Further, an investigation has been done that includes choosing and improving ML algorithms and assessing the models' performance. Discussion: Prediction plots, residual plots, and evaluation metrics plots are prepared to gauge the performance of the developed models. Thus, the research enhances AM capabilities by applying predictive modeling to process parameters and improving the quality and reliability of fabricated components. [ABSTRACT FROM AUTHOR]

Using a cutting-edge net-shape manufacturing technique called Additive Layer Manufacturing (ALM), highly complex components that are not achievable with conventional wrought and cast methods can be produced. As a result, the aerospace sector is paying closer attention to using this technology to fabricate superalloys based on nickel to develop the holistic gas turbine. Because of this, there is an increasing need for the mechanical characterisation of such material. Conventional mechanical testing is hampered by the limited availability of material that has been processed, especially given the large number of process factors that need to be assessed. Thus, the present study focuses on manufacturing CM247LC Ni-based superalloy with exceptional mechanical characteristics by laser powder bed fusion (L-PBF). This study evaluates the effect of input process variables such as laser power, scan speed, hatch distance and volumetric energy density on the mechanical performance of the LPBF CM247LC superalloy. The maximum value of as-built tensile strength obtained in the study is 997.81 MPa. Plotting Pearson's heatmap and the Feature importance (F-test) was used in the data analysis to examine the impact of input parameters on tensile strength. The accuracy of the tensile strength data classification by machine learning algorithms, such as k-nearest neighbours, Naïve Baiyes, Support vector machine, XGBoost, AdaBoost, Decision tree, Random forest, and logistic regression algorithms, was 92.5%, 83.75%, 83%, 85%, 87.5%, 90%, 91.25%, and 77.5%, respectively. [ABSTRACT FROM AUTHOR]

This article details the existing wearable assistive devices that could mimic a human's active range of motion and aid individuals in recovering from stroke. The survey has identified several risk factors associated with musculoskeletal pain, including physical factors such as engaging in high-intensity exercises, experiencing trauma, aging, dizziness, accidents, and damage from the regular wear and tear of daily activities. These physical risk factors impact vital body parts such as the cervical spine, spinal cord, ankle, elbow, and others, leading to dysfunction, a decrease in the range of motion, and diminished coordination ability, and also influencing the ability to perform the activities of daily living (ADL), such as speaking, breathing and other neurological responses. An individual with these musculoskeletal disorders requires therapies to regain and restore the natural movement. These therapies require an experienced physician to treat the patient, which makes the process expensive and unreliable because the physician might not repeat the same procedure accurately due to fatigue. These reasons motivated researchers to develop and control robotics-based wearable assistive devices for various musculoskeletal disorders, with economical and accessible solutions to aid, mimic, and reinstate the natural active range of motion. Recently, advancements in wearable sensor technologies have been explored in healthcare by integrating machine-learning (ML) and artificial intelligence (AI) techniques to analyze the data and predict the required setting for the user. This review provides a comprehensive discussion on the importance of personalized wearable devices in pre- and post-clinical settings and aids in the recovery process. [ABSTRACT FROM AUTHOR]

Utilizing Machine Learning (ML) to oversee the status of hobbing cutters aims to enhance the gear manufacturing process's effectiveness, output, and quality. Manufacturers can proactively enact measures to optimize tool performance and minimize downtime by conducting precise real-time assessments of hobbing cutter conditions. This proactive approach contributes to heightened product quality and decreased production costs. This study introduces an innovative condition monitoring system utilizing a Machine Learning approach. A Failure Mode and Effect Analysis (FMEA) were executed to gauge the severity of failures in hobbing cutters of Computer Numerical Control (CNC) Hobbing Machine, and the Risk Probability Number (RPN) was computed. This numerical value aids in prioritizing preventive measures by concentrating on failures with the most substantial potential impact. Failures with high RPN numbers were considered to implement the Machine Learning approach and artificial faults were induced in the hobbing cutter. Vibration signals (displacement, velocity, and acceleration) were then measured using a commercial high-capacity and high-frequency range Data Acquisition System (DAQ). The analysis covered operating parameters such as speed (ranging from 35 to 45 rpm), feed (ranging from 0.6 to 1 mm/rev), and depth of cut (6.8 mm). MATLAB code and script were employed to extract statistical features. These features were subsequently utilized to train seven algorithms (Decision Tree, Naive Bayes, Support Vector Machine (SVM), Efficient Linear, Kernel, Ensemble and Neural Network) as well as the application of Bayesian optimization for hyperparameter tuning and model evaluation were done. Amongst these algorithms, J48 Decision tree (DT) algorithm demonstrated impeccable accuracy, correctly classifying 100% of instances in the provided dataset. These algorithms stand out for their accuracy and efficiency in building, making them well-suited for this purpose. Based on ML model performance, it is recommended to employ J48 Decision Tree Model for the condition monitoring of a CNC hobbing cutter. The emerging confusion matrix was crucial in creating a condition monitoring system. This system can analyze statistical features extracted from vibration signals to assess the health of the cutter and classify it accordingly. The system alerts the operator when a hobbing cutter approaches a worn or damaged condition, enabling timely replacement before any issues arise. [ABSTRACT FROM AUTHOR]

This study was designed to examine the effects of a trimethylolpropane trioleate (TMPTO)-based lubricant on thrust force and torque under the high-speed drilling of Al-6061 as an effective environmentally friendly cutting fluid. The tribological performance of three lubricant blends was evaluated based on ASTM standards. TMPTO base oil, notably enhances load-carrying capacity under extreme pressure conditions, with a seizer load of 7848 N. The best-performing oil was further optimized using a Taguchi-based design experiment to investigate the effect of different additive concentrations on thrust force and torque under actual contact conditions. Experiments were conducted using three critical machining parameters: additive concentration, spindle speed, and feed rate. The results of the ANOVA analysis reveal that spindle speed contributes most substantially (62.99%) to torque, with feed rate (23.72%) and additive concentration (7.74%) also showing significant impacts. On the other hand, thrust force is primarily influenced by feed rate (73.52%), followed by spindle speed (16.82%), and additive concentration (6.28%). Furthermore, a machine learning model was developed to predict and compare a few significant aspects of high-speed drilling machinability, including thrust force and torque. Three different error metrics were utilized in order to assess the performance of the predicted values, namely the coefficient of determination (R2), mean absolute percentage error (MAPE) and mean square error (MSE), which are all based on the coefficient of determination. Compared to other models, decision tree produces more accurate prediction values for cutting forces. The present study provides a novel approach for evaluating the most promising biodegradable lube oils and predicting cutting forces by formulating a perfect blend. [ABSTRACT FROM AUTHOR]