Computer Numerical Control Research Articles

Optimised LightGBM-based health condition evaluation method for the functional components in CNC machine tools under strong noise background

Abstract The accurate health condition evaluation of the functional components in computer numerical control (CNC) machine tools is an important prerequisite for predictive maintenance and fault warning. The vibration signals of the functional components in CNC machine tools often contain substantial noise, impeding the extraction of relevant health condition information from the vibration signals. This work presents an approach that leverages the variational mode decomposition (VMD) enhanced by the Artificial Hummingbird Algorithm (AHA) alongside the Light Gradient Boosting Machine (LightGBM) optimised through particle swarm optimisation (PSO) to evaluate the health condition of the functional components in CNC machine tools amidst pervasive noise. Initially, the AHA optimised the penalty factor (α) and the decomposition layer (K) within the VMD. This optimised VMD was subsequently applied to denoise the original vibration signals. After this denoising process, PSO was employed to optimise the learning rate and maximum tree depth within LightGBM. Health condition evaluation experiments were executed on the feed system and spindle of the CNC machine tool to validate the proposed methodology. Comparative analysis indicates that the proposed method attains paramount accuracy and computational efficiency, which are crucial for accurately evaluating the health condition of the functional components in CNC machine tools.

Toolpath smoothing with reduced curvature and synchronized motion for hybrid robots

G01 commands are the most commonly used toolpath format in Computer Numerical Control (CNC) machining. Due to the discontinuity between adjacent linear segments, toolpath smoothing is necessary to improve machining efficiency and machined surface quality. This paper proposes an analytical C3 continuous local toolpath smoothing and synchronization method for a five-axis hybrid robot. Position and orientation smoothing are decoupled, with quintic B-spline segments replacing the original linear segments. The curvatures of the toolpath are reduced under constrained smoothing errors by weaving transition splines along the linear segments instead of confining them within the corners. A synchronization method based on arc length parameterization tailored to the smoothing method is also proposed. Tool tip position and tool axis orientation are synchronized using another monotonic, C3 continuous spline, which achieves smoother joint motion along the toolpath. For the hybrid robot with highly nonlinear kinematics, improved results in feedrate scheduling considering joint constraints can be realized. Simulations and experiments validate the effectiveness of the proposed method.

Development of A Tool Condition Monitoring System for Flank Wear in Turning Process Using Machine Learning

Computer-numerical control (CNC) machining has become the norm in most manufacturing businesses. In order to maximize machining efficiency, prevent unintended damage, and maintain product quality all at once, tool wear measurement is essential. Wear on the tools is typically an inevitable side effect of machining. Because it endangers the machining process, flank wear, the most frequent type of tool wear, should be avoided. This study's objective is to fill this growing need by developing a system that can use machine learning to monitor tool condition during the turning process using MATLAB. The regression method with boosted decision trees and SVR with Gaussian kernels are applied to predict the flank wear based on the vibration signal and cutting parameters. This study found that the regression with boosted decision tree method has a lower mean average percentage error, 6.43%, while SVR is 10.11%. Plus, R2 for regression is slightly better than SVR. It shows that the system successfully produced an accurate prediction of flank wear.

A full 3D reconstruction of rail tracks using a camera array

This research addresses limitations found in existing 3D track reconstruction studies, which often focus solely on specific rail sections or encounter deployment challenges with rolling stock. To address this challenge, we propose an innovative solution: a rolling-stock embedded arch camera array scanning system. The system includes a semi-circumferential focusing vision array, an arch camera holder, and a Computer Numerical Control machine to simulate track traverse. We propose an optimal configuration that balances accuracy, full rail coverage, and modelling efficiency. Sensitivity analysis demonstrates a reconstruction accuracy within 0.4 mm when compared to Lidar-generated ground truth models. Two real-world experiments validate the system's effectiveness following essential data preprocessing. This integrated technique, when combined with rail rolling stocks and robotic maintenance platforms, facilitates swift, unmanned, and highly accurate track reconstruction and surveying.

On the thermal impact during drilling operations in guided dental surgery: An experimental and numerical investigation

In recent years, a major development in dental implantology has been the introduction of patient-specific 3D-printed surgical guides. The utilization of dental guides offers advantages such as enhanced accuracy in locating the implant sites, greater simplicity, and reliability in performing bone drilling operations. However, it is important to note that the presence of such guides may contribute to a rise in cutting temperature, hence increasing the potential hazards of thermal injury to the patient's bone. The aim of this study is to examine the drilling temperature evolution in two distinct methods for 3D-printed surgical dental guides, one utilizing an internal metal bushing system and the other using external metal reducers. Cutting tests are done on synthetic polyurethane bone jaw models using a lab-scale automated Computer Numeric Control (CNC) machine to find out the temperature reached by different drilling techniques and compare them to traditional free cutting configurations. Thermal imaging and thermocouples, as well as the development of numerical simulations using finite element modeling, are used for the aim. The temperature of the tools' shanks experienced an average rise of 2.4 °C and 4.8 °C, but the tooltips exhibited an average increase of around 17 °C and 24 °C during traditional and guided dental surgery, respectively. This finding provides confirmation that both guided technologies have the capability to maintain temperatures below the critical limit for potential harm to bone and tissue. Numerical models were employed to validate and corroborate the findings, which exhibited identical outcomes when applied to genuine bone samples with distinct thermal characteristics.

Integrated Controller Design and Application for CNC Machine Tool Servo Systems Based on Model Reference Adaptive Control and Adaptive Sliding Mode Control.

In order to reduce the effect of nonlinear friction and time-varying factors on the servo system of a computer numerical control (CNC) machine tool and improve its motion control accuracy, this paper uses an adaptive sliding mode control (ASMC) method based on model reference adaptive control (MRAC). The method adopts ASMC in the control outer loop and obtains the optimal control parameters by making the sliding mode control (SMC) law continuous and adaptively estimating the control parameters. At the same time, MRAC is used in the control inner loop to enhance the "invariance" of the controlled object so that the switching gain of SMC can satisfy the disturbance matching condition even under lesser conditions. Simulation and experimental results show that compared with the traditional SMC, the ASMC based on MRAC proposed in this paper effectively reduces the influence of nonlinear friction on the system performance, and the reduction in following error reaches 71.2%, which significantly improves the motion control accuracy of the control system. The spectral analysis of the following errors shows that the maximum magnitude reduction rate of the high-frequency chattering is 89.02%, which significantly reduces the effect of the high-frequency chattering and effectively improves the stability performance of the control system.

Influence of rock properties on thrust and torque during rock coring operations a case study

The most important parameters for rock strength evaluations in excavation, mining, and mechanical engineering projects are the uniaxial compressive strength, Brazilian tensile strength, density, abrasivity, and impact strength index. To estimate these parameters, several laboratory investigations and nondestructive methods were proposed. The possibility of using time-saving models for predicting uniaxial compressive strength (UCS), Brazilian tensile strength (BTS), density, abrasivity, and impact strength index was investigated because of the difficulties in core specimen preparation. The novelty of this investigation was the prediction of rock properties using thrust and torque generated during rock coring operations. For this purpose, drilling experiments were conducted on seven different types of rock samples using a computer numerical control drilling machine. Based on the statistical analysis, simple linear regression equations were proposed for estimating rock properties, such as compressive strength, tensile strength, density, abrasivity, and impact strength index. The coefficient of determination (R 2), values obtained for thrust are 90.8, 93.3, 80.7, 87.6, and 96.3%, for compressive strength, tensile strength, density, abrasivity, and impact strength index, respectively. Whereas the corresponding torque values are 84.9, 83.9, 95.9, 81.6, and 82.6%. The developed models can be used in the exploration and excavation developments for the prediction of rock properties.

A comprehensive assessment on surface quality of machined wooden products via Box-Behnken design method

The present research work corresponds to the improvement of surface quality in the computer numerical control (CNC) machining of wooden products. In order to study the research results, the response surface methodology has been employed. Machining variables include the feed rate, spindle speed, step over, and depth of cut in three levels, and based on the Box–Behnken design method, 27 experimental tests have been performed using a 3-axis CNC milling machine. Verification of the proposed model with different points of view has been done and its accuracy has been confirmed. According to the Pareto chart of the standardized effects, the maximum influence of CNC machining variable on the surface quality of wooden products was related to the depth of cut (about 45%). In the optimal state, the surface roughness of the final specimen was computed to 3.38 μm, which was improved by 14% and 58%, respectively, compared to the best and worst cases of the practical tests.

Relationship between exposure to metalworking fluids and nonalcoholic fatty liver disease.

The relationship between metalworking fluids (MWFs) and nonalcoholic fatty liver disease (NAFLD) has not been previously explored. We aim to investigate the relationship between occupational exposure to MWFs and the prevalence of NAFLD and to determine the cumulative exposure threshold per day. In 2020, 2079 employees were selected randomly from one computer numerical control machining factory in Wuxi for a questionnaire survey, and occupational health examinations were conducted at the affiliated branch of Wuxi Eighth People's Hospital. MWF samples were collected within the factory using the National Institute for Occupational Safety and Health (NIOSH) 5524 method. NAFLD was defined as having a hepatic steatosis index (HSI) ≥ 36 without significant alcohol consumption. The relationship between NAFLD and MWFs was analyzed using logistic regression, and the daily exposure threshold was calculated using R software. MWF exposure was found to be a risk factor for NAFLD in exposed workers compared to the non-exposed group. The OR for NAFLD in workers exposed to MWFs compared to controls was 1.42 (95% CI: 1.04-1.95). An increased risk of NAFLD was shown to be associated with an increasing dose. The daily exposure dose threshold to MWFs was found to be 6.54mg/m3 (OR = 2.09, 95% CI: 1.24-3.52). An association between occupational exposure to MWFs and NAFLD was found. As the concentration of exposure rose, the prevalence of NAFLD was also escalated.

Optimization-based non-equidistant toolpath planning for robotic additive manufacturing with non-underfill orientation

Additive manufacturing (AM) technology has achieved universal application in a great number of fields, such as aerospace, medicine, and military industry. As a significant factor causing weak mechanical properties and part flaws, underfill is inevitable in AM based on the conventional equidistant toolpaths with a limited extra cost. To eliminate underfill caused by sharp corners and voids, this paper develops an optimization-based non-equidistant toolpath, i.e., isoperimetric-quotient-optimal toolpath (IQOP). Firstly, an optimization problem minimizing the isoperimetric quotient of toolpaths is designed to generate smooth toolpaths and is convexified. Then, a unilateral rolling circle method is proposed to guarantee the well-defined condition of the optimization-based toolpath planning process. Finally, the application of the depth tree makes the IQOP method adopt slices with complex boundaries and topological structures. The experimental results show that the proposed IQOP achieves an average 88.5% lower underfill rate than the contour-parallel toolpath (CP). IQOP significantly outperforms the dense CP (DCP) on toolpath smoothness and printing efficiency, with better performance on underfill. With obvious advantages on toolpath smoothness and underfill rate, IQOP achieves higher printing quality than CP in the real world. The proposed approach also provides a general framework of non-equidistant toolpath planning for complex slices in AM and computer numerical control (CNC) milling.

Data Acquisition and Performance Analysis of Image-Based Photonic Encoder Using Field-Programmable Gate Array (FPGA)

With the continuous advancement of numerical control technology, the requirements for the position detection resolution, precision, and size of photoelectric encoders in computer numerical control machine tools are increasingly stringent. In the pursuit of high resolution and precision, this work investigates the principles of electronic subdivision and embedded hardware. It designs a high-precision image-based photonic encoder using a Field-Programmable Gate Array (FPGA). This photonic encoder captures the pattern of a rotating code disk using a complementary metal-oxide-semiconductor (CMOS) image sensor. The encoder’s core is the XC6SLX25T chip from the Spartan-6 series, with peripheral circuits including only A/D sampling and low-pass signal processing circuits. The FPGA module handles the digital signal reception, waveform conversion, quadrature frequency coarse count calculation, fine count subdivision calculation, and final position calculation of the encoder. In experiments, the output signal of the photonic encoder contains many impurities. After processing by the signal processing module, the A and B phase signals are not affected by previous interference, with a phase difference of 90°, meeting the requirements for subsequent signal processing modules. After fine count subdivision processing, the waveform graph significantly increases within one cycle, and after quadrupling the frequency, 30 subdivisions are performed within each cycle. Noise is introduced into graphic positioning or graphics are positioned under different noise conditions. Experimental results show that utilizing an improved centroid algorithm helps further suppress noise and enhance measurement accuracy in the design of image-based photonic encoders.

Acceleration mechanism of abrasive particle in ultrasonic polishing under synergistic physical vibration and cavitation: Numerical study

Ultrasonic technology is widely applied in the engineering ceramic polishing processes without the limitation of material properties and ideally integrated into computer numerical control system. Ultrasonic-induced cavitation and mechanical vibration effect could accelerate the motion of solid abrasives. The individual behaviors of microjet/shockwave of ultrasonic cavitation in gases and liquids, and micro-abrasives with simple harmonic vibrations in solids and liquids has been extensively studied. To conduct a systematic and integrated study of abrasives behavior in the polishing contact region involving abrasive, surround-workpiece wall, ultrasonic physical vibration, and ultrasonic cavitation impact, a novel model integrating the free abrasive motion velocity and fixed abrasive indentation depth under multi-scale contact was proposed according to Hertzian contact theory, Greenwood-Williamson model, indentation deformation theory, the basic equations of cavitation bubble dynamics, cavitation impact control equations, and Newton's law of motion equation. The effects of ultrasonic amplitude, ultrasonic frequency, preloading force and particle size on the proposed model were investigated by theoretical analysis and numerical simulations. Ultrasonic physical vibration mainly influences the dynamic gap and further influence the number of different abrasives. Furthermore, the indentation depth of fixed abrasive depends mainly on the abrasive geometry. As the contact gap and abrasive size decrease, the indentation depth gradually decreases. Under the synergistic effect of cavitation-induced shock wave and microjet, the velocity of free abrasive in this paper is generally 0–150 m/s, and the kinetic energy of free abrasive increases roughly linearly with increasing frequency and approximately as a quadratic function with increasing particle size. Increasing the preloading force leads to a reduction in the abrasive kinetic energy. Besides, the kinetic energy induced by the shock wave has a cliff-like increment at an amplitude of 0.7–0.8 μm. It is revealed that the abrasive kinetic energy is suppressed by the cavitation bubble expansion and collapse at smaller ultrasonic pressure amplitude and surround-wall distance. This research provides a theoretical reference for the modeling of potential defects and material removal on the workpiece surface caused by abrasive motion during polishing, and reduces the trial cost for parameter optimization in actual polishing processing.

Machine Learning in Precision Manufacturing: A Collaborative Computer and Mechanical Engineering Perspective

Precision manufacturing, characterized by the production of intricate components with stringent tolerances, has witnessed a paradigm shift with the integration of machine learning (ML) techniques. This research paper delves into the collaborative endeavors between computer and mechanical engineering disciplines, exploring how the fusion of expertise from both domains contributes to the optimization and advancement of precision manufacturing processes. [1] The motivation behind this research stems from the recognition of ML's transformative potential in revolutionizing precision manufacturing. This paper reviews the application of ML in key areas such as predictive maintenance, process optimization, quality control, and adaptive manufacturing strategies. It emphasizes the synergy between computer and mechanical engineers in designing and implementing intelligent algorithms that harness data from various sensors, enabling real-time adjustments to manufacturing parameters. Predictive maintenance emerges as a critical aspect of the collaborative efforts, where ML algorithms analyze sensor data to predict equipment failures, thereby reducing downtime and maintenance costs. Process optimization is explored through the integration of ML in Computer Numerical Control (CNC) machining, highlighting how algorithms optimize tool paths and enhance machining precision. Quality control in precision manufacturing is addressed by intelligent systems that utilize computer vision and sensor technologies, providing real-time defect detection. [2] The collaborative approach presents challenges, including data security and privacy concerns and the need for skillset integration between computer and mechanical engineering disciplines. The paper concludes by exploring future directions, including the integration of emerging technologies such as edge computing and the Internet of Things (IoT), underscoring the importance of interdisciplinary collaboration for the successful implementation of ML techniques in achieving heightened precision, efficiency, and quality in precision manufacturing.

Building an Arduino Based Computer Numerical Control Router

Building an Arduino Based Computer Numerical Control Router

Investigation of computer numerical control wood milling parameters for occupationally safer by the minimization of produced wood dust

ABSTRACT Computer numerical control (CNC) wood machining produces wood dust, harming the operator's health. In this research, the effective parameters of the amount of produced wood dust (PM) in CNC milling are investigated. The design of the experiment was done based on the response surface method (RSM) and subsequently, 27 experimental tests were performed. The results of the analysis of variance show that the parameters of the depth of cut (ap ), step over (ae ), feed rate (vw ) and cutting speed (vc ) have a great impact on PM, respectively. Changing these machining parameters leads to severe changes in the PM (0.043–11.200 mg/m3). Also in 78% of experimental tests, the amount of PM is higher than the National Institute for Occupational Safety and Health (NIOSH) standard value (1 mg/m3). In the next step, for the reduction and minimization of PM, a quadratic regression equation was derived. After model validation, the model was minimized by the distance-based optimality method at Minitab software. Optimization result shows that by choosing the optimum parameters ap = 3 mm, vw = 50 mm/s, vc = 15,393 rpm and ae = 6.270 mm, PM is reduced to 0.011 mg/m3, which is much lower (about 89%) than the NIOSH standard value. This prediction was tested and validated by the experimental test.

Hardware–Software Embedded System for Real-Time Trajectory Planning of Multi-Axis Machine Using B-Spline Curve Interpolation Algorithm

This paper proposes a B-spline trajectory algorithm to realize multi-axis trajectory interpolation and analyzes the operating accuracy in an embedded system. However, the existing trajectory generation method needs to use computer-aided manufacturing (CAM) software to convert the interpolating trajectory into G code and download the code into the computer numerical control (CNC) system for processing. In this paper, the method of third-degree B-spline interpolation is proposed to generate a curved surface trajectory, and the trajectory generated by this algorithm can be run directly into a CNC system. The precision analysis of the ISO parameter segmentation interpolation algorithm and the theory of constant velocity motion is also presented. The significance of this project is that it designs a complete set of embedded systems, including hardware circuit design and software logic design, and uses low-cost STM32 architecture to realize a B-spline constant-speed interpolation algorithm, which is verified on CNC polishing equipment. A simulation conducted with the MATLAB software and the B-spline curve interpolation experiments performed on a multi-axis polishing machine tool demonstrate the effectiveness and accuracy of the optimized third-degree B-spline algorithm.

A novel method for intersecting machining feature segmentation via deep reinforcement learning

Machining feature segmentation is a primary task in machining feature recognition, as it directly impacts downstream activities such as feature type identification and process planning. However, the intersecting and overlapping of multiple machining features within intersecting machining features disrupt the original geometries and topologies, resulting in complex structures and varied forms. Therefore, segmenting intersecting machining features is highly challenging. Existing methods for intersecting machining feature segmentation often suffer from issues related to poor effectiveness and the difficulty of applying segmentation results to subsequent process planning. To address these concerns, this paper presents a novel framework for segmenting intersecting machining features using deep reinforcement learning. The framework takes intersecting machining features represented by attributed adjacency graphs as input and generates isolated machining features as output. Leveraging the robust feature representation, decision-making, and automatic learning capabilities of deep reinforcement learning, this framework enhances the effectiveness of intersecting machining feature segmentation. Moreover, the framework takes into account the machining process when designing the reward mechanism, thereby ensuring that the results are beneficial to subsequent process planning. In the experimental studies, plenty of intersecting machining features from 2.5D computer numerical control parts are used as examples to verify the feasibility and effectiveness of the proposed approach. The experimental results demonstrate that the proposed approach successfully addresses some existing challenges faced by several state-of-the-art methods in intersecting machining feature segmentation. The findings highlight the robustness of the proposed approach and its potential to address the challenges associated with intersecting machining feature segmentation. Consequently, this study contributes to the advancement of machining feature recognition and holds practical implications for process planning.

Optimizing student learning in Computer Numerical Control subject: A comprehensive analysis of influential factors

The learning outcomes achieved by students are influenced by many factors. This study aims to determine the level of support of factors (motivation, interest, family, teacher's role, learning methods and learning facilities) that influence the learning process in achieving student learning outcomes in CNC learning in class XI. The subjects in the study were Class XI students majoring in Mechanical Engineering at SMK Negeri 5 Padang in the 2022/2023 academic year totalling 37 people. Because the number of research subjects (population) is less than 100 people, so all of them are taken as samples or total sampling. Data collection was carried out using observation, questionnaires and documentation. Data analysis techniques using descriptive statistical techniques. From the data analysis, it shows that of each factor studied, the learning facility factor has the lowest level of support for student academic success compared to other factors that have been studied by researchers. Therefore, learning facilities at SMK Negeri 5 Padang in CNC subjects need to be improved again to support the student learning process and achieve better learning achievements for students.

A New Dynamics Analysis Model for Five-Axis Machining of Curved Surface Based on Dimension Reduction and Mapping

The equipment used in various fields contains an increasing number of parts with curved surfaces of increasing size. Five-axis computer numerical control (CNC) milling is the main parts machining method, while dynamics analysis has always been a research hotspot. The cutting conditions determined by the cutter axis, tool path, and workpiece geometry are complex and changeable, which has made dynamics research a major challenge. For this reason, this paper introduces the innovative idea of applying dimension reduction and mapping to the five-axis machining of curved surfaces, and proposes an efficient dynamics analysis model. To simplify the research object, the cutter position points along the tool path were discretized into inclined plane five-axis machining. The cutter dip angle and feed deflection angle were used to define the spatial position relationship in five-axis machining. These were then taken as the new base variables to construct an abstract two-dimensional space and establish the mapping relationship between the cutter position point and space point sets to further simplify the dimensions of the research object. Based on the in-cut cutting edge solved by the space limitation method, the dynamics of the inclined plane five-axis machining unit were studied, and the results were uniformly stored in the abstract space to produce a database. Finally, the prediction of the milling force and vibration state along the tool path became a data extraction process that significantly improved efficiency. Two experiments were also conducted which proved the accuracy and efficiency of the proposed dynamics analysis model. This study has great potential for the online synchronization of intelligent machining of large surfaces.

Time Series Prediction for Energy Consumption of Computer Numerical Control Axes Using Hybrid Machine Learning Models

The prediction of energy-related time series for computer numerical control (CNC) machine tool axes is an essential enabler for the shift towards autonomous and intelligent production. In particular, a precise prediction of energy consumption is needed to determine the environmental impact of a product and the optimization of its production. For this purpose, a novel approach for predicting high-frequency time series of numerically controlled axes based on the program code to be executed is presented. The method involves simulative preprocessing of the input NC code to determine each axis’s acceleration, velocity, and process force. Combined with the material removal rate, these variables are input for a machine learning (ML) model that delivers axis-specific high-frequency time series predictions. Compared to common approaches, it is thus possible to make predictions for the variable energy consumption of machine tools for any tool path or target resolution in the time domain. Experiments show that this approach achieves a high precision when a robust learning data basis is available. For the X-, Y-, and Z-axis, errors of 0.2%, −1.09%, and 0.09% for aircut and of 0.15%, −3.55%, and 0.08% for material removal can be achieved. The potentials for further improvement are identified systematically.