Edge-AI Enabled Predictive Maintenance for CNC Machines Using Real-Time IoT Sensor Analytics

The enveloping surface is formed of characteristic lines (also called contact line) at all different enveloping moment, a novel CNC (computerized numerical control) machining method based on enveloping characteristic for enveloping surface is proposed in this study. In the proposed method, the characteristic line is the machining unit, the CNC machining is driven by the characteristics lines, the CNC machining tool path distribution along the characteristics lines rather than the traditional CNC machining tool path such as contour layered,etc. In addition, the envelope characteristic automatic recognition algorithm and kinematics model of CNC machining are proposed to achieve the CNC machining based on enveloping characteristic. Finally, the proposed CNC machining method and traditional CNC machining method for single-enveloping surface and double-enveloping surface are conducted as, for instance, the machining experiment results confirm that the proposed methodology enables the machining precision and efficiency to be successfully improved. Hence, the novel CNC machining method proposed in this study is an effective technology to further improve the machining precision and efficiency of enveloping surface.

Rotating machines have become indispensable in every field of life. Because of people's commitment to machines, the machine's faults have devastating consequences. Fault analysis of devices is common in the industry. Studies in the literature mostly work on simple models. These simple models become inefficient as data complexity increases. In this paper, three types of faults are detected in the drill bit of the CNC (Computer Numerical Control) machine. Deep LSTM (Long Short-Term Memory)-based classification model has been proposed for fault diagnosis of CNC machines. Different structures can be combined to obtain higher accuracy rates. The proposed method consists of two stages: (I) the feature extraction including time, frequency domain, and Morlet wavelet coefficients information from vibration signals from CNC machines, (II) the classification of fault types using deep LSTM model based on the extracted features. LSTM structures having two layers, three layers, four layers, and five layers have been proposed and then compared with each other with respect to the classification accuracy of fault diagnosis. The highest accuracy rate obtained in this study was 99.53%. It can be seen that deep LSTM gives outstanding results in the structures with sequential data input and the proposed system gives promising results in the field of fault analysis of machines.

This paper presents a JavaScript-based approach for image-to-G-code conversion in CNC (Computer Numerical Control) machine control. The developed code enables the translation of images and text into machine-readable instructions for precise reproduction using CNC machines. The code implements image loading, preprocessing, binarization, thinning, and G-code generation functionalities. It offers adjustable parameters for CNC and image settings, allowing customization and optimization of the machining process. Experimental evaluations confirm the code's efficiency, accuracy, and usability. The results demonstrate reliable image preprocessing, effective binarization techniques, successful image thinning, and precise G-code generation. The code's accessibility, user-friendly interface, and real-time preview capabilities further enhance its usability. This JavaScript-based approach contributes to the integration of digital workflows into CNC machining, offering a promising solution for accurate and efficient fabrication.

Predictive maintenance (PdM) represents a transformative approach in modern manufacturing, aiming to forecast equipment failures through data analysis rather than relying on scheduled or reactive maintenance. This research presents a comprehensive deep learning-based framework for the predictive maintenance of Computer Numerical Control (CNC) machine tools, which are critical and costly assets in precision manufacturing. The proposed system utilizes a multi-sensor data fusion strategy, acquiring real-time operational data including vibration, acoustic emission, spindle current, and temperature. A hybrid deep learning model is developed, integrating Convolutional Neural Networks (CNNs) for automatic feature extraction from high-dimensional sensor signals and Long Short-Term Memory (LSTM) networks to capture temporal dependencies and degradation trends. The model is trained on historical run-to-failure data to learn the complex mapping between multi-modal sensor inputs and the Remaining Useful Life (RUL) of critical components such as spindle bearings and ball screws. Experimental validation is conducted on a three-axis CNC milling machine under controlled operational loads. The results demonstrate that the proposed CNN-LSTM model achieves superior predictive accuracy compared to traditional machine learning benchmarks like Support Vector Regression and standalone neural networks. The system successfully identifies incipient fault conditions with a high degree of precision, providing early warnings significantly ahead of functional failure. This capability enables optimal maintenance scheduling, minimizes unplanned downtime, reduces maintenance costs, and extends the operational lifespan of CNC machinery. The study confirms the significant potential of deep learning in enhancing the intelligence and reliability of industrial predictive maintenance systems.

CNC PCB Milling and Wood Engraving Machine incorporates the plan and usage of a CNC (Computer Numerical Control) machine to make PCB (Printed Circuit Board) and wood etching machine in a solitary set up. Creation of PCB in the present market is intensely costly when manufacture of testing circuits is considered. Along these lines, this CNC PCB Milling machine would be an effective instrument through which circuit can be scratched and penetrated at a reasonable cost. The creation of this CNC machine is to diminish the cost and multifaceted nature of machine. This venture manages the plan of programmed scaled down CNC machine for PCB drawing and processing. The proposed venture would be profoundly practical in contrast with that of customary manufacture hardware.

Computer Numerical Control (CNC) machining is a subtractive manufacturing technique that removes layers of material from a blank or workpiece to create a specific product. With increasing global competition, minimizing downtime during production is essential to maximize machine availability and productivity. This study investigates the application of machine learning models, specifically Extreme Gradient Boosting (XGBoost) and Random Forest (RF), to forecast CNC machine downtime from multiple failure sources. The study uses data collected from 16 CNC machines at Company A in Malaysia over an extended period. The data contain key variables for each downtime event, such as machine ID, failure type, start date/time, end date/time, and downtime duration in minutes. Failure types are categorized into several groups, including mechanical, electrical, and tool malfunctions. After hyperparameter tuning, the XGBoost model outperformed the RF model, achieving a Mean Squared Error (MSE) of 0.4017, Root MSE (RMSE) of 0.634, and Mean Absolute Error (MAE) of 0.470 on the test set, while the RF model yielded higher errors, with an MSE of 1.2654, RMSE of 1.125, and MAE of 0.943. These results demonstrate the superiority of the XGBoost model over RF in predicting future CNC downtime, as indicated by its lower prediction errors. Future work should focus on refining the model with larger, more diverse datasets and exploring its integration into AI-based decision support systems to enhance machine availability and operational efficiency.

Computer numerically controlled (CNC) machines have long been known and used in various industrial sectors such as the aircraft, shipping, automotive, molding and others industries. Various types of existing CNC machines such as CNC turning, CNC milling, CNC shaping, CNC drilling, CNC laser cutting and others have been commonly used in various manufacturing industries. CNC machines for production units and training unit CNC machines can be used according to milling machining parameters, machine capacity, product quality targets and workpiece material types. In milling machining using a 3-A training unit CNC machine, the first step is to design a workpiece, design G and M codes, simulate it using software such as CAD / CAM and can also be done by simulating it with a pen plotter. After evaluating and the simulation results are in accordance with the workpiece design, it can be executed for product machining. Different designs of CNC machining products have different toolpaths. In general, there are three types of techniques for path generation tools, namely iso-parametric, iso-planner, and iso-scallop height. Tool path generation on UMSU CNC milling machining using the CNC TU-3A has been developed a toolpath generation suitable for the UMSU machining. The type of tool path generation technique to be used can be considered from several factors including the complexity of the product design, the type of milling tool used, product quality, machining time and other factors.

A realtime curvature-smooth interpolation scheme and motion planning for CNC machining of short line segments

Introduction. Modern mechanical engineering is characterised by a constant increase in the proportion of parts with complex configurations (bodies of revolution with rectilinear and curvilinear elements) manufactured using materials with special physical and mechanical properties. The production of such complex components requires high precision, flexibility, and efficiency. The complex shape and variety of technological manufacturing processes are most effectively determined by their efficient processing on automated multifunctional equipment with a central processing unit (CPU). Aim and tasks. This study aims to investigate the processing of complex-shaped details made of difficult-to-process materials on Computer Numerical Control (CNC) or CNC machining is the automated control of machine tools by a computer lathes to increase the efficiency of the technological process. Results. The efficiency of the technological process has been increased when processing complex-shaped parts made of difficult-to-process materials on CNC lathes, as a methodology has been developed for determining cutting modes using the criterion of “processing productivity”. The main task at the technological preparation stage of production is optimisation in determining the parameters of the cutting mode, based on the criterion of “durability at maximum productivity”. In the developed methodology for determining the cutting mode, the volume of material removed per unit time is used as a criterion for “processing productivity”, while simultaneously taking into account the relationship between ар, f, and vc through the cutting power and tool durability, which allows an increase in productivity of up to 74%. Multi-pass roughing is more effective for CNC lathes than single-pass, and maximum cutting productivity is achieved at maximum tool feed. Conclusions. The analysis showed that productivity gains from increasing the cutting depth are limited by machine power. Optimisation based on the "tool life at maximum productivity" criterion is effective only when the machine power is not a limiting factor. It was found that reducing the target tool life (T) does not always increase productivity. Reducing T is effective only in conditions where higher cutting speeds do not exceed the available machine power; otherwise, the actual tool life may even increase. The optimisation of T must consider machine power limitations: reducing T is effective only when higher cutting speeds do not exceed the permissible power.

Any field will strive for continuous development; this is not only in the aspect of economic but also in the technological and environmental standpoint. Nowadays, technological advancement is embedded with environmental concern too; for instance, the computer numerical control (CNC) machining means of manufacture is reported to have more sustainable feature over the conventional machining means of manufacture. However, the field survey across Fiji manufacturing industries revealed that there was less usage of CNC machines. Also, it reveals that there is less awareness on the sustainability standpoint. However, the aim of the study is about identifying the current barriers and understand the nature of those barriers that limits machining industries progress towards CNC usage. Several barriers are identified from the literature survey, which was narrowed down to eight essential barriers by conducting a questionnaire survey with industrial and academic experts. These barriers are analysed using interpretive structural modelling and decision‐making trial and evaluation laboratory hybrid approach. The discussion is made to understand the interrelationship or the cause and effect relationship between the barriers. The outcomes of this study create awareness in education to increase graduates or technicians understanding CNC machines and to align curriculum accordingly for industrial applications.

Nowadays, computer numerical control (CNC) machine tool undertakes more processing tasks than other common machine tools because of its highly automated machining ability and high performance. However, due to the lack of intelligence in machining process planning, machining procedure of products mostly depends on process planners rather than CNC machine tools. To make product quality less dependable on process planner’s ability and improve the efficiency of process planning in order to fulfill changeable market, this paper presents an approach to design and develop CNC machining process knowledge base using cloud technology. The general standard STEP-NC is mapped to web ontology language (OWL) to describe machining process-related knowledge in a readable and comprehensible way. This mapping relation also makes knowledge suitable for storage in HBase. Through this ontology model, descriptive and logical knowledge can be collected. Hadoop platform is used in this approach to provide the NoSQL database HBase for large-scale knowledge storage and MapReduce programming model for large-scale knowledge processing. Taking advantage of MapReduce, knowledge query engine and reasoning engine can be developed. Users can submit task and resource descriptive files to the cloud through CNC controller and get machining process solutions from knowledge base. Evaluation mechanism is also adopted to filter low-quality knoweldge.

High-quality material manufacture requires the improvement of the computer numerical control (CNC) machine performance. Such task can be achieved by considering the tool trajectory, in which it is important to minimize the acceleration and jerk levels. Previous research works are focused on providing smooth movements at most with C2 continuous trajectories, and the results of using C3 continuity in the trajectory are not evaluated. The contribution of this study is the design of a methodology for obtaining C3 tool trajectories while acceleration and jerk levels are constrained through adaptive feed-rate. C3 and C2 trajectories are executed in a CNC machine. Speed, acceleration, and jerk are monitored in order to validate the proposed methodology and to analyse and quantify the differences between using C2 and using C3 trajectories.

This paper introduces a new intelligent integration between an IoT platform and deep learning neural network (DNN) algorithm for the online monitoring of computer numerical control (CNC) machines. The proposed infrastructure is utilized for monitoring the cutting process while maintaining the cutting stability of CNC machines in order to ensure effective cutting processes that can help to increase the quality of products. For this purpose, a force sensor is installed in the milling CNC machine center to measure the vibration conditions. Accordingly, an IoT architecture is designed to connect the sensor node and the cloud server to capture the real-time machine’s status via message queue telemetry transport (MQTT) protocol. To classify the different cutting conditions (i.e., stable cutting and unstable cuttings), an improved model of DNN is designed in order to maintain the healthy state of the CNC machine. As a result, the developed deep learning can accurately investigate if the transmitted data of the smart sensor via the internet is real cutting data or fake data caused by cyber-attacks or the inefficient reading of the sensor due to the environment temperature, humidity, and noise signals. The outstanding results are obtained from the proposed approach indicating that deep learning can outperform other traditional machine learning methods for vibration control. The Contact elements for IoT are utilized to display the cutting information on a graphical dashboard and monitor the cutting process in real-time. Experimental verifications are performed to conduct different cutting conditions of slot milling while implementing the proposed deep machine learning and IoT-based monitoring system. Diverse scenarios are presented to verify the effectiveness of the developed system, where it can disconnect immediately to secure the system automatically when detecting the cyber-attack and switch to the backup broker to continue the runtime operation.

Incremental Sheet Forming is a rather new forming process which is used to obtain complex three dimensional parts by stretching the sheet with a pin tool whose path is controlled by a CNC machine. This study presents a new fixture design for Single Point Incremental Forming (SPIF) and experiments conducted for two profiles. Single Point Incremental Forming is used for small and batch production. The fixture presented in this study was made using mild steel which can be used for performing multiple forming purposes. The circular profile and a square profile were generated using a spherical head tool of 5mm diameter made of Stainless steel and the results were compared with that of Simulations for the same profiles using the analysis software, ABAQUS. The experiments were carried out using Computer Numerical Control (CNC) machine.

According to the literature review, limited studies were performed related to the production of "without fastener and ready to assemble (RTA)" furniture made of wood-based panel materials with Computer Numerical Control (CNC) machines and the evaluation of their strength. The aim of this study was to evaluate the cyclic loading performance of different types of RTA chairs without fastener which produced with CNC machines by using engineering design approach and product engineering methods including performance tests. In the production of chairs, 18 mm thick oriented strand board, medium density fiberboard and Oriental beech plywood were utilized as wood-based panels. Within the scope of the study, 4 different chair types without fasteners were designed and produced, and performance tests were carried out in 3 different loading directions (front to back, back to front and side thrust) with cyclic stepped increasing loading method according to the principles of American Library Association specification. Totally, 108 real size chairs without fastener were prepared and tested. As a result of the study, it was concluded that the chairs produced from Oriental beech plywood gave the best performances, while the chairs produced from medium density fiberboard gave performance values close to Oriental beech plywood, except for the side thrust test. However, the mechanical performance values of the chairs constructed of oriented strand board were very low. In conclusion, it could be said that the chairs constructed of Oriental beech plywood and medium density fiberboard without fastener have been found to have sufficient mechanical performance.