Milling Machine Research Articles

Investigation of the influence of electrolytic milling machining parameters on the machining accuracy of thin-walled parts.

Aircraft parts are often designed as thin-walled structures to reduce the weight of the aircraft. However, thin-walled structures are prone to deformation during the milling process, leading to a decrease in machining accuracy. To address this problem, a method combining milling and electrochemical machining, known as electrolytic milling, is proposed to minimize deformation and enhance the accuracy of thin-walled parts. The factors that affect the machining accuracy of electrolytic milling were analysed, and a model for predicting the thickness of the material removed was established. Electrolytic milling experiments were designed, and the model was solved. Based on the built model, the influences of feed rate, spindle speed, radial cutting depth, voltage and electrolyte concentration on material removal thickness were investigated. Compared with the milling method, the electrolytic milling method can improve the machining accuracy of thin-walled parts. Electrolytic milling experiments were conducted on box-shaped parts to verify the reliability of the proposed method.

Milling Machine Fault Diagnosis Using Acoustic Emission and Hybrid Deep Learning with Feature Optimization

This paper presents a fault diagnosis technique for milling machines based on acoustic emission (AE) signals and a hybrid deep learning model optimized with a genetic algorithm. Mechanical failures in milling machines, particularly in critical components like cutting tools, gears, and bearings, account for a significant portion of operational breakdowns, leading to unplanned downtime and financial losses. To address this issue, the proposed method first acquires AE signals from the milling machine. AE signals, capturing the dynamic responses of machine components, are transformed into continuous wavelet transform (CWT) scalograms for further analysis. Gaussian filtering is applied to enhance the clarity of these scalograms, effectively reducing noise while maintaining essential features. A convolutional neural network (CNN) based on the VGG16 architecture is utilized for spatial feature extraction, followed by a bidirectional long short-term memory (BiLSTM) network to capture the temporal dependencies of the scalograms. The genetic algorithm (GA) is used to optimize feature selection and ensure the selection of the most relevant features to further improve the model’s performance. The optimized features are finally fed into a fully connected (FC) layer of the proposed hybrid model for fault classification. The proposed method achieves an accuracy of 99.6%, significantly outperforming traditional approaches. This method offers a highly accurate and efficient solution for fault detection in milling machines, allowing for more reliable predictive maintenance and operational efficiency in industrial settings.

PERFORMANCE ANALYSIS OF ELECTROMAGNETIC VIBRATION ENERGY HARVESTING DUE TO DIFFERENT VIBRATION SOURCES

As industry requires more real-time monitoring and interconnected systems, the need for wireless sensors will increase. Vibration Energy Harvesting (VEH) has played an important role as an alternative energy source to provide power to wireless sensors. In this paper we report the analysis of an electromagnetic energy harvester driven by vibrating plate. An experimental method where energy sources originating from vibrating mechanical machines were used. Mechanical machines such as milling machines, dynamic rotors, and four-stroke engines were implemented to prove the performance of the device. where the output signal from the vibration source is measured using a CF-3600 FFT analyzer, while the output signal from the electromagnet is measured using an oscilloscope (Hantek 6022BE). This paper has discussed several sources of vibration originating from industrial equipment with a vibration source frequency of around 10 to 100 Hz. The findings show that the voltage produced by an electromagnetic energy harvester is 130 mV, 120 mV, and 30 mV on a milling machine, dynamic rotor, and four-stroke engine. Additionally, the results contribute to the optimization of vibration energy harvesting parameters, facilitating the maximization of energy extraction in diverse applications.

Estimating Operating States of Numerical Control Milling Machines Using Wi-Fi Sensing and Channel State Information

This study investigates whether wi-fi sensing, through channel state information (CSI), can estimate the operating state and the material machined by a numerical control (NC) milling machine without contact sensors. The research aims to develop a predictive system that detects machine tool failures by analyzing fluctuations in wi-fi radio waves and assesses the state of the machine based on changes in wi-fi radio waves. If a machine tool vibrates differently from usual, the system predicts a fault based on historical vibration data. To achieve this, a novel approach is required to predict the operating state of a machine tool using wi-fi sensing. Thus, this study conducted a preliminary evaluation to determine the possibility of estimating the operating state of a machine tool using wi-fi sensing. The experiment involved controlling the NC machine tool to alter its operational state during material processing and measuring the processing state using CSI obtained from a wi-fi module. Results indicated that CSI can estimate the operating and machining states of the milling machine.

A framework for data-driven decision making in advanced manufacturing systems: Development and implementation

Integration of sophisticated technologies such as Internet of Things, cyber physical systems and big data analytics have revolutionized the advanced manufacturing systems (AMS). However, implementation of data-driven decision making in AMS still remains challenging due to data heterogeneity, real-time processing demands, and integration complexities. This paper overcomes this challenge by presenting a novel framework for adoption of DDDM in AMS to enhance its decision-making capabilities. This framework consists of six stages: manufacturing stage, sensing stage, data stage, knowledge stage, decision stage, and application stage. The proposed framework leverages big data analytics to extract actionable insights from diverse datasets, integrates CPS to create a seamless interaction between physical and digital systems, and employs IoT technologies for real-time data acquisition and monitoring. The framework is validated through a comprehensive case study involving a CNC milling machine dataset, demonstrating significant improvements in operational efficiency, decision accuracy, and response time. The case study involves detailed data collection steps, preprocessing, and analysis, showcasing the framework’s practical implementation and effectiveness. The results show that the proposed framework addresses existing challenges and provides a scalable solution for DDDM implementation in AMS.

Classification of faults in friction stir processed composites using a machine learning and ensemble learning approach

Abstract Aluminium alloy based surface composites with hard reinforcement particles have wide scope in aerospace and automobile manufacturing industries. In this paper, the aluminium composites, manufactured by friction stir processing (FSP) with varying parameters are investigated for the faults occurred during fabrication process. It explores a machine-learning approach to detect defects of surface hybrid composites with an Al6061 alloy matrix, reinforced with copper and graphene nano-powders, using friction stir processing and a tungsten carbide tool on a milling machine. Multi-sensor time series data (vibration, force, and current) collected during fabrication, is preprocessed and labelled with normal and defective categories (e.g., pin break, brazing break, rough surface, no composite) using visual inspection. The important time domain and frequency domain features are extracted using different libraries in python. Thenafter, various types of feature selection techniques, viz filter, wrapper and embedded methods are implemented to select most relevant features. The selected subset of features from all selection methods used, are applied to different machine learning and ensemble learning classifiers and their performances are evaluated. The optimal combinations of the type of feature selection method and classifier used, are obtained for efficient classification of surface defects in composited formed by FSP. The real time monitoring and defect detection system can be developed in future for the composites developed by FSP using the developed models.

Tool wear prediction based on K-means and Adaboost auto-encoder

Abstract A new tool wear prediction model is proposed to address the tool wear issue, aimed at monitoring tool wear based on specific task requirements and guiding tool replacement during actual cutting operations. In the data preprocessing phase, tool wear states are classified using unsupervised K-means clustering. The time, frequency, and time-frequency domain features are then labeled and fused using an autoencoder neural network applied to the original set of signal features from the tool. For tool wear prediction, an enhanced autoencoder neural network leveraging AdaBoost is employed to establish the prediction model. The reconstruction error serves as the chosen loss function to assess the autoencoder's performance, taking into account data correlation and the inherent lossy nature of the autoencoder. Experimental results from real machining data obtained from a CNC milling machine demonstrate that the proposed model achieves higher prediction accuracy while reducing data dimensions.

Performance Analysis of Disc Mill Type FFC-15 Grinder for Making Charcoal Husk Flour

This study is motivated by the great potential of rice husk as a waste material that has not yet been optimally utilized. The focus of this research is to evaluate the performance of the FFC-15 disc mill machine in producing flour from rice husk charcoal at three different moisture contents. The variations in the moisture content of rice husk charcoal studied were 10%, 15%, and 20%, with the goal of determining the optimal conditions in the production process of rice husk charcoal flour. The methodology used is experimental with repeated testing to produce data on machine capacity, electrical power consumption, flour yield, flour quality (moisture content, ash content, and mineral content), and the physical parameters of the charcoal. The results show that moisture content significantly affects the milling efficiency and quality of the flour produced, with optimal conditions achieved at a moisture content of 10%. Adjusting the moisture content before the milling process can enhance the operational efficiency of the machine and the quality of the final product. These findings are expected to provide benefits for follow-up by a group or industry that wants to optimize the utilization of rice husk charcoal. Keywords: Disc mill FFC-15, Flour quality, Husk charcoal, Milling efficiency, Moisture content.

Application of The Reverse Engineering In The Modelling of A Blade and Screen In A Hammer Mill

PT XYZ plans to produce coconut shell briquettes. Currently, PT XYZ already has a hammer millmachine that will be used in the production process. A hammer mill machine is a machine that servesto smooth the material. Before carrying out mass production, a simulation is carried out first. Themanufacture of briquettes found obstacles in the process of grinding and screening. Coconut shellcharcoal that has been milled and entered is partially retained and cannot be released to proceed to thenext process. The grinding result is larger than the screen size, which is 1 to 2 mm. In the manufactureof briquettes, it is expected that the grinding results are less or equal to 0.4 mm. Based on theidentification of the problem, the alternative solution chosen by the researcher is to redesign thehammer mill machine, especially on the blade and screen sections. The design is done using thereverse engineering method. There are five steps in designing using this method. In the study, it wasfound that the second design was a suitable design to be developed because it was better than theexisting state. The mill results were obtained with an average of 0.0343 mm and a grinding time of186.807 seconds. The fineness values and the grinding process time were obtained throughsimulations using the EDEM 2022.1 software.

Determinants of net value added to produced and processed paddy rice in South East, Nigeria

The study principally examined the determinants of net value added to produced and processed paddy rice in South east Nigeria It specifically, identified the socio-economic characteristics of the respondents, analyzed the determinants of net value added to produced and processed paddy rice as well as ascertained the constraints to processed and produced paddy rice. Multi-stage sampling technique involving purposive and random sampling methods was used to select 240 respondents. Primary data were collected on rain-fed production season using structured questionnaires administered to the respondents by personal interview. Descriptive statistics,, multiple regression and principal component analysis were used to analyze the data. Results obtained showed that gender distribution of the respondents was 63%males and 38% females. More respondents are between the ages of 41-50 and31-40 respectively and house hold size of 4-6 .Farming experience showed that 136 respondents representing 57% had engaged in the business between 11-20yrs.The results also showed that 67% of the respondents accessed farm credit while 25% did not.66% of the respondents belonged to farmers association while 75% were not visited by extension agents. Variables (age, gender, years in school, household size, years of experience, training/extension visits, costs incurred, value addition technique and market price) significantly influenced the net value added while marital status, membership of cooperative, and access to credit did not. Constraints to paddy producers and processors were accessibility to farm machine, poor infrastructure and scarcity/high cost of labor, low access to credit/grant; low proactive measures to flood and drought control; insufficient knowledge of agro-chemicals, and late provision of essential training and services; and processors: use of outdated rice milling machines, high cost of modern rice processing machines, low access to modern rice processing machineries and low acceptability of local rice. Recommendations include; establishment of farm machinery hiring centers for producers and supply of modern rice milling machines to rice processing clusters, development of dams and irrigable lands, training and re-training on access to fund, utilization of biodegradable wastes from paddy rice, proactive measures of flood and drainage control, adequate use of agro-chemicals, use of modem techniques, and involvement of National Agency for Food and Drug Administration and Control in quality control. Keywords: Agriculture, Paddy Rice, Value Addition, Nigeria.

The Effectiveness of Implementing a Milling Process in Reducing Production Process and Costs: A Case Study

Every product's design has a different process flow. Sometimes, designed products consist of a repeated process flow. Repeated processes are a problem that can affect production management and production output. This study has potentially proposed a new process that can replace the existing process by adding a milling process. The result shows that introducing a milling process was added to item 2 to produce a step slot and reduced the number of items used (Item 3). The assembly of Item 2 and Item 3 was converted into Item 6, which showcases a more substantial time differential, with the existing process taking 12.25 minutes and the new process requiring 0 minutes. The additional process of the new alternative milling machine reveals lower Watt, less time duration for the welding machine, reduced energy consumption for a hand-grinding machine, and lower cost demand for the welding machine than the existing process. In addition, the total cost of the added milling process shows a slight reduction in overall cost and is associated with energy consumption.

An experimental study of the response characteristics of end milling operations and their finite element simulation

The present study investigates the effect of milling parameters on cutting forces and performance characteristics in end mill operations using two different types of end milling tools. The end milling experiments were performed on AA7075-T6 grade aluminium alloy using a vertical milling machine fitted with a Kistler dynamometer to acquire the data of cutting forces during the milling operation. A matrix of process parameters was created by varying spindle rotational speed in the range of 500–1200 rpm while the feed rate was kept between 10 and 30 mm/min, keeping a maximum depth of cut of 4 mm. The data obtained from the experimental results were analysed and validated by simulation using the DEFORM-3D software facility. The experimental results reflect that with the increase in cutting speed, the cutting force first increases and then decreases, while an increase in feed rate enhances the cutting forces. The combination of high cutting speed with low feed rate was found to be suitable as the force required in this case exhibits a minimum to achieve both efficiency and machinability for a tool. Validated experimental results can be useful for finding new combinations of parameters in the defined parameter range for milling applications.

Web-Based Maintenance Prediction of Machine Conditions and Failure Modes Using Machine Learning

Machine failure may result in unplanned downtime, production losses, safety risks, and increased costs. Hence, predicting machine failures is a significant challenge faced by many industries. Predictive Maintenance (PdM) techniques can help mitigate these risks by predicting machine failures before they occur. This research, therefore, develops two supervised Machine Learning (ML) algorithms to predict failure conditions and the associated failure modes for a milling machine. Six machine features were investigated. The ML models were then developed using a four-stage process including data pre-processing, training, evaluation, and deployment. Several ML algorithms were applied then the results were evaluated using accuracy, recall, precision, and [Formula: see text]1-score. The results showed that the Random Forest algorithm was the most effective in predicting machine conditions and failure modes of the milling machine. A web application for PdM was finally developed and tested for the PdM of the milling machine. In conclusion, the developed web application including ML algorithms can support the effective PdM for the machine, which leads to enhancing its availability and improving productivity. Future research considers adopting ML algorithms for predicting machine conditions and failure types of other machines.

Explainable AI based Predictions for Workpiece Quality

It is well known that sound emissions of drilling and milling machines can be used to predict process and work piece quality. Deep Learning models have successfully been applied for that task. However, artificial neural networks are perceived as black boxes as the inference mechanisms of the network are not transparent. In this paper we present a Convolutional Neural Network trained on audio data with which process and product quality of a milling process can be controlled. The model was trained on 10-second audio snippets recorded from a milling machine that were converted into spectrograms. The trained model classifies the drilling process and predicts the expected workpiece quality. Additionally, rough estimates of the center rough and average roughness depth values are predicted. Moreover, we apply the Explainable AI methods that produce explanations by highlighting sections of the spectrogram that were relevant for the prediction. The spectrograms enriched with the explanations provide insights into the decision making process of the deep learning model in a human interpretable form. Patterns of how and why of a prediction become visible. Areas considered relevant by the model can be compared to the expectations of the human user. Through this explanation component, the model is not only able to make predictions but also to increase trust in the system which is an important aspect of acceptance of AI based quality assurance.

Optimising Sensor Placement for Tool Condition Monitoring: A Comparative Analysis of Acoustic Emission Data

In the monitoring of machining processes and in the context of tool condition monitoring, the position of acoustic emission sensors affects the quality of the resulting information. This drives this comparative study which presents a comparison of acoustic emission data recorded simultaneously by a sensor attached to the side of the milling table and another sensor near the spindle during a tool wear test on a CNC milling machine. The signal information is clearly influenced by the different positions. Whereas the signals near the spindle are dominated by vibrations of the spindle motor during machining, these strong contributions do not occur in the recorded data of the machining process detected by the sensor mounted to the table. However, the position of the sensor near the spindle has the advantage of maintaining a constant distance to the source of the acoustic emissions of the machining process, as the sensor moves with the tool. In contrast, the sensor attached to the milling table is affected from the fact that the distance to the milling tool is constantly changing. This results in different dominant frequencies, that are analysed in this study. To analyse both the entire frequency range and the higher frequencies, two distinct approaches are employed, one without and one with the use of a high-pass filter. Furthermore, the recorded signals were used to calculate the characteristic features, namely the Partial Powers, thereby enabling assessment of the condition of the tool. The results demonstrate that this single feature type is sufficient for training a machine learning model to predict the tool wear, focusing on the flank wear width. This study analyses the efficiency of wear prediction with respect to both sensors and frequency spectra, and compares the results. In this context, the most accurate predictions were achieved with Gaussian process regression models.

EVALUATING THE MARGINAL DISCREPANCY AND SURFACE ROUGHNESS OF CAD - CAM MILLED VS 3D PRINTED PROVISIONAL CROWNS - AN INVITRO STUDY

Aims &Objectives: To evaluate Marginal discrepancy and Surface roughness of CAD-CAM Milled and 3D Printed provisional crowns after subjecting them to thermocycling. Materials and Methods: A stainless-steel metal die with ANSI/ADA specifications had been fabricated for the study. It was scanned with an intraoral scanner and the data was sent to VHF S5M CAD CAM milling and R3Pro printing machine. A total of 10 samples Milled Group A(n=10) and 10 Printed Group B(n=10) provisional crowns were fabricated from PMMA material using the scanned data. The temperatures for thermocycling are 37ºC and 60ºC. Each group is subdivided into two subgroups(n=5) based on thermocycling temperatures. The timeduration selected for Thermocycling was 7,14 and21 days. Marginal discrepancy was measured by using Stereomicroscope and Surface roughness was measured with Profilometer. Results: Marginal discrepancy values were greater in CAD CAM milled crowns(141.47 µm) than in Printed crowns(109.87 µm) at 60ºC after a time-period of 21days.Surface roughness values were higher in Milled crowns(3.915µm) than in CAD CAM Printed crowns(3.817µm) at 60ºC for a given time duration of 21days. One-way ANOVA statistical analysis was done. The mean marginal gap of CAD CAM Milled crowns was statistically significant than Printed crowns(p>0.05). Conclusion: Printed provisional restorationshad better Marginal accuracythan CAD CAM Milled provisional crowns. Surface roughness was higher in CAD CAM Milled crowns than in Printed provisional restorations.

Gap compensation control method for robotic electrochemical milling machining based on multi-physics field coupling

Gap compensation control method for robotic electrochemical milling machining based on multi-physics field coupling

Parametric investigation of laser incidence geometry in laser-assisted milling of Inconel 718

While laser-assisted milling machining is promising for promoting the machinability of Inconel 718, the geometrical parameters of laser beam relative to milling tool significantly influence its machining performance. In this work, we investigate the effects of various parameters of laser incidence geometry on the laser-assisted milling process of Inconel 718 by comprehensively employing analytical investigations, finite element simulations and experiments. Firstly, a laser-assisted milling experimental platform is constructed, and a fully coupled thermal-mechanical 3D finite element model of laser-assisted milling of Inconel 718 is established. Secondly, experiments and finite element simulations of laser-assisted milling of Inconel 718 are conducted to investigate the impact of laser assistance on cutting force and machined surface morphology. Results indicate that laser-assisted milling can moderately reduce cutting force and enhance surface quality compared to conventional milling. Thirdly, a single-factor experiment is carried out to explore the impact of laser incidence geometry parameters (laser power, laser incidence angle, and laser spot-tool edge distance) on the cutting force in laser-assisted milling of Inconel 718. Furthermore, the parametric investigation based on the response surface methodology is carried out to assess the coupled effects of the three parameters for deriving their optimal values. The experimental results show that the optimized parameters of laser-assisted milling can lead to a 47.4% reduction in surface roughness and a 25% reduction in cutting force, accompanied by significantly reduced tool wear, as compared to conventional milling. The findings demonstrate that the rational selection of laser incidence geometrical parameters is crucial for enhancing the laser-assisted milling capability for Inconel 718.

Optimization of Hammer-Disc Mill Parameters During Producing Gluco-mannan Flour Using Taguchi Method

Porang tubers contain glucomannan, which has health benefits for the human body. However, glucomannan also contains calcium oxalate, which is toxic. A Hammer-Disc mill (HDM) machine was used to separate glucomannan and calcium oxalate, categorized as a mechanical process. This study aims to optimize the parameters of the Hammer-Disc Mill machine for producing glucomannan flour by using the Taguchi Method. The selected parameters are the mass of the porang chip, motor rotation speed, and the distance of the hammer blades. The Taguchi Method was used to design an experiment using the Orthogonal Array L9 (3 factors, 3 levels). In this study, statistical analysis was carried out using Analysis of Variance (ANOVA) to determine each parameter's effect on glucomannan production. The glucomannan granules were taken using a screener of 60-80 mesh. The results show that the input mass parameter of porang chips significantly affects the glucomannan produced, which, F calculating 10,91 was more than f Table 5,41. The contribution of mass input of porang chips in percentage is 85.36%. Based on the results of the best response, the optimal condition for the production of glucomannan flour is to use a mass of 1 kg of porang chip input (level 3), motor rotation speed of 3000 rpm (level 3), and hammer spacing of 1 cm (level 3). By optimizing this parameter it is expected to increase the yield of glucomannan produced by the Hammer-Disc Mill machine.

An integrated design method for remanufacturing scheme considering carbon emission and customer demands

Design for remanufacturing (DfRem) plays an important role and aims to reduce carbon emissions during the remanufacturing phase at the initial design stage. However, low-carbon requirements and customer demands are not considered integrally when generating schemes, which might to limit the potential to reduce carbon emissions. To address the problem, this paper proposes a DfRem scheme generation method that combines the Quality Function Deployment for Low-Carbon (QFDC) model with the FMAS (Functional-Motion-Action-Structure) model. Firstly, the demands are categorized into customer, remanufacturability and low-carbon demands, and the FAHP (Fuzzy Analytic Hierarchy Process) is used to evaluate the weight of demands. Secondly, the QFDC model is developed to convert demands to engineering characteristics, and to determine the design priorities. Thirdly, the FMAS model is established to map engineering characteristics into related structures, and a low-carbon and customer-satisfied DfRem scheme is generated. Finally, the efficacy of proposed method is demonstrated through a case study on the remanufacturing of a CNC milling machine, displaying its superiority in reducing carbon emissions while meeting customer demands.