Machining State Research Articles

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.

Research on the influence of cutter overhang length on robotic milling chatter stability

Serial industrial robots are widely in demand in the field of large-scale component processing and manufacturing. However, the structure characteristic of serial robots makes it easy to generate chatter during milling and the overhang length of milling cutter has an important influence on the stability of robotic milling. Milling cutter overhang length refers to the length from the tip of the cutter to the protrusion of the spindle, to study the influence of milling cutter overhang length on the stability behavior of robotic milling, the modal parameters of milling cutter under different overhang length were obtained by hammer experiment, and its dynamic characteristics were analyzed. The stability behavior for robotic milling under different cutter overhang lengths was analyzed by using the stability lobe diagrams, and the stability lobe diagrams were verified by robotic milling experiments. The results show that the rigidity and natural frequency of milling cutter decrease with the increase of overhang length. There is a big gap between the stability lobe diagrams and the actual machining state when the cutter overhang length is short, and the low frequency vibration is easy to occur in the robotic milling process when the spindle speed is low, which is most probably because that the absorbed vibration energy by the cutter has been transferred to the robot body before the milling cutter vibrates. When the cutter overhang is increased and the feed direction is along the y-axis of the robot global coordinate system, the stability lobe diagrams by considering the multi-mode coupling effect is more consistent with the actual milling state.

Pulse dynamic regulation of electrochemical discharge milling by utilizing the slotted tube electrode

Electrochemical discharge machining (ECDM) has a splendid application potential for machining difficult-to-cut materials. It is a challenge to limit and control the discharge energy and area of DC power supply in ECDM. Owing to the uncertainty and randomness of the position and range of the single discharge, the unpredictable discharges deteriorate the surface quality of the workpiece, alter the size of the inter-electrode gap (IEG), and influence the distribution of the multi-physical fields. Therefore, to regulate the machining state and energy, the ideology of pulse dynamic machining is introduced, and a method of pulse dynamic ECDM utilizing the slotted electrodes is proposed. With the tool electrode rotating, the tube electrode transforms the pure electrochemical machining (pure-ECM) stage and the electrochemical discharge machining (ECDM) stage periodically through the slots at the bottom of it. The machining current waveform, surface roughness and sidewall taper of machined grooves, material removal rate (MRR), and relative tool wear rate (RTWR) are investigated. Additionally, the discharge types of the ECDM are explicitly defined and statistically classified. The experimental results show that the pulse dynamic regulation of hybrid machining using the slotted electrodes is beneficial to regularize the machining current waveform and optimize the machining quality.

An automatic generation approach of process model based on feature knowledge and geometric modeling

Traditional process planning applies knowledge to convert design information within the part model into process information. This information is then displayed by manually drawing two-dimensional (2D) process cards from multiple views, illustrating the geometric design and the process details. However, this method has revealed several issues, including poor efficiency, information misinterpretation, and the potential for manual drawing errors. This traditional approach hampers the integration of manufacturing information across engineering software. It exacerbates the digital divide between computer-aided design (CAD), computer-aided process planning (CAPP), and computer-aided manufacturing (CAM). To address these issues, this study proposes an automated approach for creating three-dimensional (3D) process models based on feature knowledge and geometric modeling. The 3-axis milling features are recognized as the machining objects from the boundary representation (B-Rep) part model. Geometric and parameter knowledge for modeling is derived from the machining step. In the proposed approach, two geometric modeling methods are investigated to construct feature state volumes (FSVs). The first method utilizes FSV modeling to simulate the shape of unmachined features before rough machining, while the second method utilizes FSV modeling to construct the shape of machined features before finishing machining. The case studies illustrate that the proposed approach can construct FSVs for various machining states and autonomously generate process models. In digital manufacturing, this approach assists process planners in intuitively evaluating the reasonableness of process routes. Additionally, it provides the essential driving geometry required for the autonomous generation of tool paths.

Finite element analysis and experimental study on the cutting mechanism of SiCp/Al composite in laser ultrasonic elliptic vibration turning

SiCp/Al composites have excellent material properties and are increasingly being used in the aerospace, military, and electronic packaging industries. However, the inhomogeneity and non-conductivity of conventional turning (CT) results in poor material surface quality and high cutting forces, which seriously hinder the application of particlereinforced metal matrix composites. The thermal softening property of laser-assisted turning (LAT) and the intermittent cutting property of two-dimensional (2D) ultrasonic elliptical vibratory turning (UEVT) offer unique advantages in improving material surface quality. Therefore, a novel laser ultrasonic elliptical vibratory turning (LUEVT) machining technique is proposed to improve the machining of SiCp/Al composites with two different volume fractions. The effect of highfrequency intermittent machining on material processing was further investigated by adjusting the pulsed laser power. Finite element modelling was used to predict the machining state, surface roughness, and chip morphology between the workpiece and the PCD tool. The effects of varying the machining parameters during the experiment on the two composites were analysed. The results showed that the LUEVT of 25 % and 45 % SiCp/Al composites were reduced by 39.3 % and 30.7 % respectively compared to the CT cutting forces. The experiments verified the consistency of the surface roughness and chip morphology with the finite element simulation results. The stability of the cutting force during the cutting process is also improved, as the material removal process mainly takes the form of small particle fragmentation and matrix encapsulation.

Online vibration monitoring using laser vibrometer and acoustic emission techniques in robotic milling CFRP composites

Carbon fiber reinforced polymer (CFRP) material has superior mechanical properties, often utilized in the aerospace industry. However, its prone to surface defects such as burrs and delamination under the influence of machining vibration, thereby compromising component quality. This study evaluated the relevant vibration signal features via signal processing methods, and investigated the effect of machining parameters on machining stability during robotic milling of CFRP composite. Specifically, the study assessed machining status by analyzing milling signals and compared surface quality between vibration and stable machining stages, the former corresponds to a larger Sa on the machined surface, with more pronounced profile fluctuations. Machining vibration manifests distinct characteristics in laser vibrometer signals, exhibiting in time-frequency plots with short-term signal enhancements at multiple frequencies. This phenomenon occurs more frequently during entry and exit stages. The results indicated that feed speed has a limited effect on milling stability within the selected parameter range, and severe machining vibration occurred at lower spindle speed (12,000 rpm) and higher milling depth (2 mm). Corresponding surface defects formation mechanisms were discussed, revealing that the formation of uncut burrs at the top was related to axial milling force, while interlayer debonding cracks stemmed from variations in fiber orientation between adjacent layers.

A novel approach on calibration of a laser line sensor’s position in the machine coordinate system

Abstract On-machine measurement facilitates real-time monitoring and feedback of the machining status of parts, thereby preventing secondary positioning errors in the offline measurement of parts. Calibrating spatial position of the measuring sensor is crucial for ensuring the accuracy of on-machine measurements. This paper introduces a novel approach to on-machine calibration of line laser displacement sensors, based on the fitted sphere-center method and iterative position in both height and width directions along the line laser. By constructing a transformation matrix and measuring multiple sets of data to determine the unknowns in the matrix, the spatial position of the laser displacement sensor can be calibrated. The results showed that the polar deviation of the standard ball radius was 0.0067 mm, confirming the feasibility and accuracy of the method.

Detection of electrolyte supply state in the electrochemical discharge machining of micro hole based on deep learning

Electrochemical discharge machining (ECDM) is an effective technique for machining hard and brittle insulating materials due to its characteristics that the occurrence of electrochemical discharging is independent of the electrical conductivity of the workpiece. In ECDM, the machining performance is significantly influenced by the real-time machining state. However, the real-time machining state still cannot be effectively detected and fed back until now. To improve the performance of ECDM and establish a useful closed-loop control strategy, it is essential to find a new signal that characterizes the machining state. Electrolyte supply is critical for ECDM and can be used as a closed-loop control factor. In this paper, a novel method for detecting the electrolyte supply state in the machining zone based on current signals was proposed. To achieve the method, a R-BiLSTM-A (ResNet-BiLSTM-Attention) model was designed for electrolyte supply state detection. The designed model was demonstrated to perform better than the other general artificial intelligence models. The relationship between the contact force and the electrolyte supply state detection results was investigated. It was found that the electrolyte supply state was insufficient when the tool-workpiece contact occurred. This state was successfully detected by the model, which verified the effectiveness of the designed model. The proposed model was then applied to detect the electrolyte supply state under different machining conditions. The tool electrode feed rate and electrode retreat parameters were optimized based on the detection results of the proposed model. The hole depths were improved by 126.50 % and 301.69 % with optimized machining parameters at the voltage of 39 V and 43 V, respectively.

A novel method-based reinforcement learning with deep temporal difference network for flexible double shop scheduling problem

This paper studies the flexible double shop scheduling problem (FDSSP) that considers simultaneously job shop and assembly shop. It brings about the problem of scheduling association of the related tasks. To this end, a reinforcement learning algorithm with a deep temporal difference network is proposed to minimize the makespan. Firstly, the FDSSP is defined as the mathematical model of the flexible job-shop scheduling problem joined to the assembly constraint level. It is translated into a Markov decision process that directly selects behavioral strategies according to historical machining state data. Secondly, the proposed ten generic state features are input into the deep neural network model to fit the state value function. Similarly, eight simple constructive heuristics are used as candidate actions for scheduling decisions. From the greedy mechanism, optimally combined actions of all machines are obtained for each decision step. Finally, a deep temporal difference reinforcement learning framework is established, and a large number of comparative experiments are designed to analyze the basic performance of this algorithm. The results showed that the proposed algorithm was better than most other methods, which contributed to solving the practical production problem of the manufacturing industry.

In Situ Measurement of the Machining State in Small-Diameter Drilling by Acoustic Emission Sensing

In drilling small holes with diameters of 1 mm or less, minute clogging and twining of chips or the adhesion of the workpiece material can become factors in causing breakages of the drill bit; moreover, it can be difficult to identify the machining state. Acoustic emission (AE) sensing is a nondestructive inspection technique that measures the elastic-stress waves that are generated when a material is deformed and fractured. AE sensing permits highly sensitive measurements to be made without changing the rigidity of the experimental system, unlike force sensing of cutting resistance, etc. In the present study, attempts were made to identify the machining state and tool wear, and to predict abnormalities in small-diameter drilling by using the change in the frequency of AE signal waveforms arising from deformation and fracture. It was shown that it is possible to predict the breakage of the drill bit by detecting high-frequency AE signals at about 1 MHz, caused by the adhesion of the workpiece material. In addition, a correlation map of the AE frequency spectrum for identifying the machining state in a drilling operation is suggested.

Intelligent monitoring of milling tool wear based on milling force coefficients by prediction of instantaneous milling forces

The spindle current of a machine tool contains a wealth of machining information and by analyzing its signal characteristics wear monitoring of milling tools can be achieved. Most current research in tool wear monitoring has been achieved by intelligent classification methods, but such methods are unable to identify wear states when cutting parameters change. To address this challenge, the paper proposes a new tool wear monitoring framework that identifies the wear state of milling cutters under different cutting parameters. The first step is to establish the mapping relationship between the spindle current signal and the milling force signal through neural networks under a variety of cutting parameters. Based on the mapping property between two signals, a TCN-LSTM based neural network prediction model is proposed to achieve accurate prediction of milling forces by spindle current signal. Various cutting information is then calculated based on the predicted milling forces and PLC communication, and a method is proposed to identify the machining status of the tool: the milling force coefficient monitoring method. The method reflect the wear status of the milling cutter by monitoring the range of threshold values, making the identification of the tool wear state without interference from variable spindle speeds, feeds and depths of cut. The proposed method provides a new solution for tool wear monitoring, breaking the inherent thinking of intelligent tool wear classification, and the experimental results prove the effectiveness and generality of the proposed method.

Target-path planning and manufacturability check for robotic CLT machining operations from BIM information

Mass timber is one of the trending construction styles in the last years thanks to its sustainability and offsite manufacturing properties, where cross laminated timber (CLT) is the most common material used. In an effort to link design and manufacturing information in a single location, this study proposes a generative process planning algorithm for CLT machining in robotic environments. The algorithm focuses on automatic feature-based interpretation of the geometry of CLT panels to obtain the targets required to guide the robots for its machining. The method developed detects primitives geometries of the CLT panels, determines the appropriate operations (either sawing, drilling, or milling), select the robot based on manufacturing capabilities (reach and tool availability), and generates the target-path planning for its machining process. The proposed method is tested in a robotic machining station for CLT panels simulated in RobotStudio® as a case study. The results showcase the capabilities of the proposed algorithm to provide manufacturing results out of the process planning process from geometric information available at the design stage. These results include process duration, path planning, resource allocation and utilization. This study provides a framework to include manufacturing information in design decisions to facilitate planning or cost estimations and anticipate issues downstream generated during the design phase.

In-process monitoring of the ultraprecision machining process with convolution neural networks

ABSTRACT In-process monitoring and quality control are the most critical aspects of the manufacturing industry, especially in ultra-precision machining (UPM) at an industrial scale. However, in-process ensuring product quality has been difficult, as any subtle change in the process influences the UPM process dynamics and the process outcome. In order to meet the increasingly soaring demand for precision components, intelligent monitoring of the machining process is essentially important and much needed. Capturing complex signal patterns through conventional signal processing for the UPM process is often challenging due to the comparably high noise levels in the industrial environment. Signals obtained during UPM are inherent transients and non-stationary, necessitating extensive and accurate features for classification. Accurate detection of anomalies may allow for quick corrective actions, reducing the degree of damage. Earlier research revealed multi-sensor analysis, which yields richer signal feature information, but the unavoidable sensor failure in conjunction with heterogeneous sensing made it challenging. In order to address the challenges, this paper investigates the feasibility of convolution neural network (CNN) for classifying abnormal and normal machining in the UPM process. The vibrational signals obtained from B&J 4533-B accelerometer during diamond turning are transformed into time-frequency-based log-spectrogram images. These images are classified using CNN, and the results show that a proposed convolutional neural network algorithm has demonstrated an accuracy of 85.92% in classifying images and thus the corresponding in-process machining status.

Experimental Investigation of the Effects of Machining Parameters on the Performance of Form-Cutting Tools Manufactured by Wire Electrical Discharge Machining (WEDM) and Grinding Processes.

In this research, a comparison between two methods of grinding and WEDM and the chip formation of each form tool was studied through a set of designs of experiments. A multi-functional form tool with different cutting-edge shapes was designed to compare different production methods, and a grinding machine and a five-axis wire-cutting machine were made. The form tools by the wire cutting method were made with three different machining states, rough, semi-finish, and finish. The results of the experimental test showed that the chip formation of the finished surface of the wire cut tool was close to the ground tools. Additionally, the tool life in wear generation was assessed, revealing that the tool generated through the wire-cutting method with three passes exhibited superior performance compared to alternative approaches. Furthermore, employing the wire-cutting technique with high surface finishing yielded optimal outcomes for producing form-cutting tools featuring complex profiles.

Evolution of the Interelectrode Gap during Co-Rotating Electrochemical Machining

A new co-rotating electrochemical machining method is presented to machine the complex structure inside annular parts such as flame tubes and aero-engine casings. Due to the unique shape and motion of electrodes, it is difficult to accurately compute the electric field intensity in the machining area. In this paper, the complex electric field model is simplified by conformal transformation, and the analytical solution of electric field intensity is exactly calculated. A material removal model is built on the basis of the electric field model, and the dynamic simulation of the material removal process is realized. The effects of the cathode radius, applied voltage, feed rate and initial interelectrode gap on the interelectrode gap (IEG) and material removal rate (MRR) are analyzed. The simulation results indicate that the MRR is always slightly less than the feed rate in a quasi-equilibrium state, resulting in a slow reduction in IEG. In addition, the final machining state is not affected by the initial IEG, and the MRR in a quasi-equilibrium state is determined by the feed rate. Several comparative experiments were carried out using the optimized processing parameters, in which the MRR and IEG were measured. The convex structures were successfully machined inside the annular workpiece with optimum machining parameters. The experimental results are in good agreement with the theoretical results, indicating that the established model can effectively predict the evolution process of MRR and IEG.

On the transition of failure mechanisms during machining process with varied speeds: A molecular dynamics study

Conventional machining theory states that the machining of a ductile material may create continuous, serrated, and/or fragmented chips with increasing machining speeds. In this study, transitions of failure mode under varied machining speeds in single-crystalline silicon were analyzed based on molecular dynamics (MD) simulations of the ultra-high-speed machining of single-crystalline silicon. The MD simulations employ the periodic boundary conditions along the third direction which can mimic the material failure in cutting plane. The uncut depth reaches 39 nm, which is sufficiently large to accommodate complex atomic evolutions. The simulation results indicate that jetted chips occurred in front of the cutter, when the machining speed is increased to approximately 2.7 × 103 m/s, which is attributed to the shock pressure induced by the chip inertia. Essentially, the Rankine-Hugoniot jump conditions were introduced to explain the influence of the shock pressure. Both the calculations based on Rankine-Hugoniot jump conditions and the MD results imply that the shock wave speed is equal to the machining speed at the steady machining state. In addition, the transition from fragmented-chip to jetted-chip morphology exhibits a stage wherein the two primary adiabatic shear bands are simultaneously activated. The present work sheds light on the underlying mechanism of chip formation at an ultra-high-machining speed beyond 1000 m/s.

Self-adaptive micro-hole breakout detection in the electrochemical discharge drilling process based on CNN-BiLSTM

Electrochemical discharge machining (ECDM) is an effective and promising technology for the micro-hole drilling of hard and brittle insulating materials such as glass, quartz and ceramics. Hole exit quality is an important part of through-hole machining quality in ECDM. The hole exit quality is influenced by two different machining states before and after the hole breakout. Therefore, it is necessary to identify hole breakout occurrence to provide a basis for achieving a machining strategy that matches the changing machining state and thus improves the hole exit quality. However, currently, there is no effective method to detect the hole breakout in the ECDM of micro-holes. In this paper, a self-adaptive micro-hole breakout detection method based on CNN- BiLSTM was proposed. The hole breakout detection can be expressed as a binary classification problem according to the analysis of the current signals collected before and after the hole breakout. The sufficiency of the raw current signal information was discussed. A CNN-BiLSTM model was established to detect hole breakout using the current signals as the training dataset. The CNN-BiLSTM model showed better performance compared to CNN, LSTM, BiLSTM and CNN-LSTM by comprehensive considering of accuracy, F1 score, AUC value, training time, predict time, breakout detection results and Dunn test results. Furthermore, the length of current signals used for each single detection and the threshold value used for breakout detection were discussed. An optimal threshold value was calculated, and the delay of detection was within 66 ms. The proposed method was successfully applied to the hole breakout detection in the through-hole drilling experiments and the success rate was 100 %. The hole exit area just after breakout were measured and compared to the hole exit area after hole completion, the average ratios of the former to the latter were 11.69 %, 27.29 %, 38.43 % and 44.41 % for the voltage of 39 V, 41 V, 43 V and 45 V respectively.

Improving energy production by using diverse rated units in small hydropower plants

The usual criteria for designing hydropower plants include the distribution of the rated power among equally rated generating units in such way that a single spare part could be used in whatever damaged unit. However, modern cutting tools and machining stations available to the manufacturing sector allow quick production and access to the main components of hydropower plant units, including valves, turbines, and generators, in such a way that they can be immediately ordered as needed. Storing expensive spare parts is not necessary anymore, reducing the number of fixed assets, and increasing the economic feasibility of investments. Additionally, using the same rated generating units may result in undesired energy losses and operational limitations as explained in this paper. Therefore, this paper proposes a new methodology for sizing unequal units’ rate for a given hydropower plant power, updating usual criteria, maximizing the energy production and optimizing maintenance needs. The proposed method is described and applied in two case studies, resulting in energy generation improvements at more than 1% when compared with the traditional approach, which is equivalent to a reduction of at least 12.5% to about 25% of the current energy conversion losses in hydro turbines.

Electrochemical micromachining based on sinusoidal signals with variable resistance

ABSTRACT Reducing pulse duration is the sole effective strategy to improve the processing accuracy in ultra-short pulse electrochemical microfabrication. High cost and unsuitability in practical production also restrain its development. This study aims to propose a method based on sinusoidal signals with variable resistance. The bilayer capacitor cannot be fully charged to achieve a transient machining state. An equivalent circuit differential equation is established, and the resistance becomes an effective parameter to control the machining accuracy. The experimental result shows that the machining accuracy increases significantly with the increase in resistance. The approach is applied to machine microstructures and achieves sub-micron scale accuracy on a pure nickel sheet. The same superior machining accuracy can be obtained by machining microstructures on hard-to-cut superalloy plates.

Chatter detection for micro milling considering environment noises without the requirement of dominant frequency

Existing chatter detection methods were mainly developed for conventional milling processes, and did not consider the influences of environment noises. Thus, they are not suitable for micro milling, in which the widely used small cutting parameters easily lead to the occurrence of non-negligible noises. This article proposes a new variable forgetting factor recursive least-squares (VFF-RLS) algorithm to filter out the chatter-independent component, which is composed of environment noises and periodic components, for the signals sampled from the micro milling process. It is theoretically found that with the aid of VFF-RLS algorithm, there is almost nothing in the filtered signal for stable cuts, while chatter components will be dominant in the filtered signal for unstable cuts. This important finding confirms that some features can be easily extracted from the filtered signal to directly reflect the stable or unstable machining states without the requirement to measure the system’s dominant frequency, which is necessary for some existing methods to obtain the frequency band where chatter vibrations appear. Subsequently, a streaming feature selection considering feature interaction (SFS-FI) method is established to select optimal features and remove irrelevant and redundant features. Then, a chatter detection model is developed based on the selected features. Finally, a series of micro milling tests with various axial depths of cut and spindle speeds prove that the proposed model can accurately identify the cutting state, even for slight chatter and stable cuts with small little depths of cut, which are more easily disturbed by environment noises. Results confirm that the detection accuracy is larger than 99 %, and this fact means that the proposed method is effective and practical for detecting chatter occurring in micro milling processes.