Computer Numerical Control Research Articles

Wire arc additive manufacturing of a high-strength low-alloy steel part: environmental impacts, costs, and mechanical properties

Additive manufacturing (AM) technologies have demonstrated a promising material efficiency potential in comparison to traditional material removal processes. A new directed energy deposition (DED) category AM process called wire arc additive manufacturing (WAAM) is evolving due to its benefits which include faster build rates, capacity to build large volumes, and inexpensive feedstock materials and machine tools compared to more technologically mature powder-based AM technologies. However, WAAM products present challenges like poor surface finish and lower dimensional accuracy compared to powder-based processes or machined parts, prevalence of thermal distortions, residual stresses, and defects like porosity, cracks, and humping, often requiring post-processing operations like finish machining and heat treatment. These post-processing operations add to the production cost and environmental footprint of WAAM-built parts. Therefore, considering the opportunities and challenges presented by WAAM, this paper analyses the environmental impact, production costs, and mechanical properties of WAAM parts and compares them with those achieved by laser powder bed fusion (LPBF) and traditional computer numerical control (CNC) milling. A high-strength low-alloy steel (ER70S) mechanical part with medium complexity was fabricated using WAAM. Based on the data collected during this experiment, environmental impact and cost models were built using life cycle assessment and life cycle costing methodologies. WAAM was observed to be the most environmentally friendly option due to its superior material efficacy than CNC milling and has a better energy efficiency than LPBF. Also, WAAM was the most cost-friendly option when adopted in batch production for batch sizes above 3. The environmental and cost potential of WAAM is amplified when used for manufacturing large products, resulting in significant material, emission, and cost savings. The fabricated WAAM part demonstrated good mechanical properties comparable to that of cast/forged material. The methodology and experimental data presented in this study can be used to calculate environmental impacts and costs for other products and can be helpful to manufacturers in selecting the most ecofriendly and cost-efficient manufacturing process.

Modelling and optimization method for energy saving of computer numerical control machine tools under operating condition

The widespread application of machine tools in industry results in very high energy consumption. In order to save energy, it is an effective means to reduce the processing power while improving the processing efficiency of machine tools. Since milling parameters directly affect machine performance, the selection of suitable milling parameters is particularly important. In this regard, this study proposes an integrated modelling and optimization method for energy saving of computer numerical control (CNC) machine tools under operating condition. Firstly, the operating condition of the CNC machine are analyzed and the processing power and efficiency mathematical models are established based on the four milling parameters (n, fz, ae, ap). Subsequently, the Pareto optimal solution is introduced to establish an optimization model integrating the processing power and time. To solve the optimization problem, an adaptive chaotic multi-objective chimp algorithm with fast convergence and satisfactory optimization is proposed considering three aspects: search space, convergence factor, and chaotic mapping. Afterwards, further degrees of freedom and sensitivity analyses were carried out on the constructed model using the Sobol method. Finally, comparative analysis and validation are conducted through simulation cases and actual processing experiments, respectively. The results show that both validation scenarios have the same conclusion. Compared with three existing algorithms, the proposed method reduces the processing power by 5.63 %, 4.65 % and 4.51 % and improves the processing efficiency by 27.88 %, 15.11 % and 15.31 %, respectively. Based on the above enhancements, the energy consumption is reduced by 58.21 %, 45.54 % and 41.45 % respectively.

Evaluation of CNC lathe machine with fuzzy linguistic mcdm methods

CNC (Computerized Numerical Control) lathes have become integral to modern manufacturing and machining industries due to their ability to produce intricate parts with precision and efficiency. Not only do CNC lathes enhance productivity and accuracy, but they also minimize human error and enhance overall safety in the manufacturing process. Furthermore, the current market offers a wide array of diverse types of CNC lathes. Consequently, the evaluation and selection of CNC lathes pose a complex decision-making challenge as there are numerous types available, each with a variety of selection criteria for manufacturers to consider. It is crucial to make an informed choice, as improper evaluation and selection can have adverse effects on the overall performance of the production system. In this study, we propose using the fuzzy EDAS (Evaluation Based on Distance from Average Solution) model to evaluate and select CNC lathes. Initially, we employ the fuzzy analysis method, based on expert opinions, to establish a set of weights for the evaluation criteria. These criteria consist of seven factors: capital cost, spindle speed, distance between centers, rapid traverse rates in the X-axis and Z-axis, maximum machining diameter, and maximum machining length. Subsequently, the fuzzy EDAS object ranking model is utilized to evaluate and rank the CNC lathes, ultimately aiding in the selection of the most suitable machine for the manufacturer. The results obtained from our analysis reveal that the MICROTURN-300DX machine is the optimal choice, closely followed by the MICROTURN-300X machine. The study's findings serve as valuable guidelines for decision makers in selecting CNC lathes that align with the requirements of factory production. Moreover, the suggested approach can also be utilized to choose various other machine types as production demands become more intricate

Extreme roughness reduction and ultrafine quality of innovative dual function material extrusion 3D printer

PurposeThis paper aims to use hybrid manufacturing (HM) to overcome several drawbacks of material extrusion three-dimensional (3D) printers, such as low dimension ranging from 0.2 to 0.5 µm, resulting in a noticeable staircase effect and elevated surface roughness.Design/methodology/approachSubtractive manufacturing (SM) through computer numerical control milling is renowned for its precision and superior surface finish. This study integrates additive manufacturing (AM) and SM into a single material extrusion 3D printer platform, creating a HM system. Two sets of specimens, one exclusively printed and the other subjected to both printing and milling, were assessed for dimension accuracy and surface roughness.FindingsThe outcomes were promising, with postmilling accuracy reaching 99.94%. Significant reductions in surface roughness were observed at 90° (93.4% decrease from 15.598 to 1.030 µm), 45° (89% decrease from 26.727 to 2.946 µm) and the face plane (71% decrease from 12.176 to 3.535 µm).Practical implicationsThe 3D printer was custom-built based on material extrusion and modified with an additional milling tool on the same gantry. An economic evaluation based on cost-manufacturing demonstrated that constructing this dual-function 3D printer costs less than US$560 in materials, offering valuable insights for researchers looking to replicate a similar machine.Originality/valueThe modified general 3D printer platform offered an easy way to postprocessing without removing the workpiece from the bed. This mechanism can reduce the downtime of changing the machine. The proven increased dimension accuracy and reduced surface roughness value increase the value of 3D-printed specimens.

Low-cost, high-volume imaging for entomological digitization.

Large-scale digitization of natural history collections requires automation of image acquisition and processing. Reflecting this fact, various approaches, some highly sophisticated, have been developed to support imaging of museum specimens. However, most of these systems are complex and expensive, restricting their deployment. Here we describe a simple, inexpensive technique for imaging arthropods larger than 5 mm. By mounting a digital SLR camera on a CNC (computer numerical control) motor-drive rig, we created a system that captures high-resolution z-axis stacked images (6960 × 4640 pixels) of 95 specimens in 30 minutes. This system can be assembled inexpensively ($1000 USD without a camera) and it is easy to set-up and maintain. By coupling low cost with high production capacity, it represents a solution for digitizing any natural history collection.

On-Demand Transport Bubbles Adhering to Noncontiguous Patterned Superhydrophobic Surfaces Using a Superhydrophobic Tweezer.

Bubble transportation and related flotation are ubiquitous phenomena in nature and industry. Various surfaces with distinct morphologies and specific wettability properties have been engineered by organisms in nature and by humans to facilitate the targeted movement of bubbles. However, existing methods predominantly rely on continuous surfaces, limiting the ability of bubbles to deviate from their path before reaching their intended destination. Therefore, directional transportation of bubbles using noncontiguous surfaces still remains a significant challenge. Inspired by water spiders' ability to capture bubbles underwater using their hydrophobic surface for survival, we propose a novel transport strategy that utilizes patterned superhydrophobic surfaces (PSHSs) and a superhydrophobic tweezer. This strategy is implemented by switching between the hood mode and puncture mode of the moving three-phase contact lines to load and unload the bubble. To quantitatively evaluate the loss ratio of the bubble during transportation, a simple and exquisite bubble-weighing apparatus is devised. Our findings indicate that circular PSHSs demonstrate superior bubble adhesion and achieve the highest bubble transport ratio of 95.1%. In order to validate the promising application of this novel method, we employ the computer numerical control (CNC) technology to facilitate the autonomous loading and precise transportation of underwater bubbles, as well as the blending and ionization of combustible gas bubbles with air bubbles at different volume ratios.

A Mathematical Modeling of Computer Numerical Control Skiving Process for Manufacturing Helical Face Gears Using Sensitivity Matrix Combined With Levenberg–Marquardt Algorithm

Abstract Currently, numerous studies have applied gear skiving processes to produce face gear. However, there remains a significant challenge in achieving a flexible computing model for manufacturing a precise tooth surface for face gear. This study proposes a novel mathematical model that combines the cutter modification method and computer numerical control (CNC)-axis motion modification methods within a unified “closed-loop optimization.” This approach aims to enhance the tooth surface accuracy of skived helical face gears by determining optimal coefficients. Applying the Levenberg–Marquardt algorithm and sensitivity matrix enables the calculation of new polynomial coefficients, ensuring the attainment of gear surfaces with an accuracy grade of B6 (according to the ANSI/AGMA 2009-B01 standard) for each target surface. The proposed methodology involves the generation of a helical skiving cutter using a corrected rack. Subsequently, the cutting path on the CNC machine is optimized by incorporating additional motions expressed in polynomials. A comprehensive skiving simulation is conducted to achieve the desired face-gear surface, which is corrected by specified polynomial coefficients. The proposed model is validated through numerical and machining simulations using vericut software. The results affirm the practicality and efficacy of our approach in achieving the desired accuracy in producing helical face gears through power skiving processes.

A visualization study of a confined vapor chamber with conical microstructure applied in data centres

Abstract With the development of the informatization technology, the scale of the data centre is expanding rapidly. The energy consumptions of the electronic equipment in the data centre are rising regularly, which lead to the thermal management becoming an argent issue to be settled. To realize the sustainable development of green data centre, the passive two-phase vapor chamber (VC) has turned into the focus of electronic cooling research. Constructing nucleation induced structures on the evaporation surface is an effective method to improve the performance of the vapor chamber. To address the problem of achieving enhanced boiling, a novel conical microstructure was designed in the vapor chamber with 50 mm height. The conical structure of 1 mm axial height was fabricated on the evaporation surface by computer numerical control (CNC) machining technology. A visualization experimental system was developed to investigate the effect of the conical microstructure on the two-phase behaviours, and the boiling heat transfer characteristics under different heating conditions (Q in = 35 W, 50 W, 65 W) in a confined vapor chamber. The high-speed camera was used to capture the bubble behaviours. Experimental results found that compared with the smooth surface, the integration of the conical structure increasing the number of bubble nucleation sites and the bubble departure frequency. The bubble growth period at stable heating stage is 162 ms shorter than initial heating stage on the evaporation surface with conical structure. The thermal resistance (R vc) of vapor chamber with conical structure is improved by 5.85% compared to the smooth one at Q in = 65 W, which indicate that the conical microstructure can enhance the boiling heat transfer performance. This study aims to provide a reference for the design of thermal management system for green data centre.

Feedrate-preserved motion planning for five-axis directed energy deposition of freeform metal parts

Laser-powder DED (LP-DED) has been investigated extensively for the rapid prototype of complex and customized metallic parts and in-situ repairing tasks. However, unlike the material extrusion type which allows a relatively large overhang angle, the conventional 2.5-axis LP-DED faces a severe overhang issue that deteriorates the printing stability and quality. While five-axis LP-DED is able to effectively resolve the overhang problem, it however introduces new kinematic issues and limited nozzle orientation range due to physical restrictions of DED. The existing computer numerical control systems are mainly designed for machining, where the above issues can be mostly solved by feedrate scheduling, which, however, is not applicable for LP-DED processes, as the feedrate must be preserved as programmed lest deposition height would be altered since in most cases it is not practical to vary the powder flow rate in real-time. In this paper, a feedrate-preserved motion planning method is proposed to optimize the rotational angles of the machine tool in the machine coordinate system (MCS) under the constraints of MCS and workpiece coordinate system (WCS). Given a five-axis DED path as well as its accompanying initial nozzle orientation in WCS, we first map them via inverse kinematics to MCS, which is represented by a cylindrical coordinate system. Then, the motion path in the cylindrical coordinate system is optimized to avoid the singularity. Finally, the physical constraint of nozzle orientation in WCS is introduced into the time-weighted constrained Laplacian smoothing in MCS with the axial speed limits upheld. The experimental results confirm that the actual feedrate is successfully preserved as the theoretical one under the constraints of the axial kinematic limits, while the singularity is avoided.

Comparative Evaluation of the Mechanical and Physical Properties of Mineral Trioxide Aggregate vs. Bacterial Cellulose Nanocrystal-Reinforced Mineral Trioxide Aggregate: An In Vitro Study.

This study aims tocompare and assess the compression strength, microhardness, and surface texture of two sets of materials: mineral trioxide aggregate (MTA) PlusTMand bacterial cellulose nanocrystal (BCNC)-reinforced MTA PlusTM. According to the ASTM E384 standard, the cylindrical molds made of plexiglass with an internal diameter of 6 mm and a height of 4 mm were fabricated using computer numerical control laser cutting. A total of 20 samples (n=10) in each group were considered in this experimental study: Group I (control group) MTA PlusTM (Prevest DenPro Limited, India)and Group II (experimental group) BCNC (Vedayukt India Private Limited, India)-reinforced MTA PlusTM. After preparation, the molds were incubated at 37°C in a fully saturated condition for about 24 hours, and then the compression strength, microhardness, and scanning electron microscopy analyses were performed at different magnifications. The obtained data were then statistically analyzed. Quantitative analysis revealed that there is a statistically significant difference between MTA PlusTM and BCNC-reinforced MTAPlusTM (p<0.002). The Wilcoxon signed-ranktest and Mann-Whitney U-test revealed that BCNC-reinforced MTA PlusTM showed significantly higher compression strength (33.80±3.83 MPa, p=0.00) and surface microhardness (642.85±24.00 μm, p=0.00) than the control group. Based on ourfindings, it was concluded thatthere is a statistically significant difference between both study groups. Thus, incorporating BCNC into the MTA PlusTM significantly increased the compression strength and surface microhardness of the MTA PlusTM cement. Numerous dental applications have been investigated for bacterial cellulose. Many benefits of bacterial cellulose are available, which includeits effects on moldability, low cost, high water retention capacity, biocompatibility, and biodegradability. Furthermore, the addition of BCNC to MTA PlusTM accelerates the material's hardening process and decreases its setting time, which in turn shortens clinical chairside procedural timing and thereby improves patient satisfaction.

Mini-ridge filter designs for conformal FLASH proton therapy

The present study designed a mini-ridge filter capable of generating a 30 mm spread-out Bragg peak (SOBP) specific to the proton FLASH beamline for use in proton FLASH mouse studies. Proton FLASH therapy delivers ultra-high dose rates exceeding 40 Gy/s, necessitating instantaneous SOBP generation via static method. The TOol for PArticle Simulation (TOPAS) was used to model the FLASH beamline, which enabled accurate replication of beam characteristics identified from measurements, and ensured accurate dose calculations. Comparisons between simulated and measured peak widths and R80d values, accurate to within 1 mm, verified the accuracy and reliability of Monte Carlo code. Two mini-ridge filters of different materials were designed and optimized using MATLAB, simulated with TOPAS for SOBP verification, and fabricated using 3D-printing or computer numerical control manufacturing. The results indicated strong agreement between the simulated and measured SOBP widths for the polylactic acid mini-ridge filter but with discrepancies observed in the range and flatness measurements, which may be due to the use of 3D printing. By contrast, the aluminium alloy mini-ridge filter achieved excellent results, generating a 31.6 mm SOBP width with 0.89% flatness. Therefore, the present study validated the accuracy of our Monte Carlo code in simulating the FLASH beamline and the feasibility of our mini-ridge filters.

Advanced Monitoring of Manufacturing Process through Video Analytics.

The digitization of production systems has revolutionized industrial monitoring. Analyzing real-time bottom-up data enables the dynamic monitoring of industrial processes. Data are collected in various types, like video frames and time signals. This article focuses on leveraging images from a vision system to monitor the manufacturing process on a computer numerical control (CNC) lathe machine. We propose a method for designing and integrating these video modules on the edge of a production line. This approach detects the presence of raw parts, measures process parameters, assesses tool status, and checks roughness in real time using image processing techniques. The efficiency is evaluated by checking the deployment, the accuracy, the responsiveness, and the limitations. Finally, a perspective is offered to use the metadata off the edge in a more complex artificial-intelligence (AI) method for predictive maintenance.

Rotation Error Prediction of CNC Spindle Based on Short-Time Fourier Transform of Vibration Sensor Signals and Improved Weighted Residual Network.

The spindle rotation error of computer numerical control (CNC) equipment directly reflects the machining quality of the workpiece and is a key indicator reflecting the performance and reliability of CNC equipment. Existing rotation error prediction methods do not consider the importance of different sensor data. This study developed an adaptive weighted deep residual network (ResNet) for predicting spindle rotation errors, thereby establishing accurate mapping between easily obtainable vibration information and difficult-to-obtain rotation errors. Firstly, multi-sensor data are collected by a vibration sensor, and Short-time Fourier Transform (STFT) is adopted to extract the feature information in the original data. Then, an adaptive feature recalibration unit with residual connection is constructed based on the attention weighting operation. By stacking multiple residual blocks and attention weighting units, the data of different channels are adaptively weighted to highlight important information and suppress redundancy information. The weight visualization results indicate that the adaptive weighted ResNet (AWResNet) can learn a set of weights for channel recalibration. The comparison results indicate that AWResNet has higher prediction accuracy than other deep learning models and can be used for spindle rotation error prediction.

Muqarnas in Islamic Architecture: Development, Materials, and Techniques

Muqarnas was first created during the first millinium AD and became a defining feature of Islamic architecture during the second mellinium, specifically between the 11th and 16th centuries, both in religious and secular contexts. Although largely abandoned by the 17th century, the use of muqarnas decoration reached its peak during the above period. This study examines muqarnas, its three-dimensional architectural embellishment, as well as its development and influence on modern architecture. For this purpose, the descriptive analytical approach was employed. Architectural surveys were carried out at the local level, while textual analysis was done to analyze the historical development. The history of muqarnas was traced from Islamic religious buildings to modern architecture. It was found that digital technologies including Computer Aided Design (CAD) and computer numerical control (CNC) have influenced muqarnas pattern design and rebirth in the 20th and 21st centuries. Both ancient and modern muqarnas use isometries and symmetry, although their design procedures are different. Parametric design and CAD tools allow the current muqarnas to be dynamic and flexible, unlike the traditional ones. The current research underlines that regionally available materials and pattern availability affect the design of muqarnas. Early manifestations of muqarnas were used to fragment squinches, which ultimately led to the creation of an aesthetically pleasing formal mechanism and a system of three-dimensional decoration. In the middle period, muqarnas was also used as decorative carvings on structural member. At present, lightweight materials such as fiberglass and pre-fabricated muqarnas are preferred in contemporary architecture, although the details of muqarnas are still maintained for their aesthetic value. The geometry used to calculate muqarnas has remained the same since its development, regardless of the materials used. This research stimulates the design of new muqarnas patterns for aesthetic purposes and building performance optimization. Modern architecture uses muqarnas compositions and digital technologies to reflect the traditional cultural and historical patterns, creating a developing trend.

The Development Trends of Computer Numerical Control (CNC) Machine Tool Technology

The Development Trends of Computer Numerical Control (CNC) Machine Tool Technology

Predictive modelling of residual stress in turning of hard materials using radial basis function network enhanced with principal component analysis

This study proposes a hybrid machine learning (ML) model that combines a radial basis function network (RBFN) with principal component analysis (PCA) to predict residual stress (RS) in the machining process. Higher temperatures and plastic deformation can generate RS conditions in the machining of hard materials, significantly influencing the quality of machined parts, particularly their surface integrity. It is crucial to evaluate and guarantee machining conditions that ensure reliable surface integrity that yields compressive RS conditions. Incorrect parameter settings can lead to poor surface quality, resulting in tensile RS conditions that impact both the quality and lifetime of manufactured products. The methodology involved experimental machining trials for data acquisition, with conditions selected for hard material machining tests conducted using a computer numeric control (CNC) lathe under dry cutting conditions. The cutting force components were measured, and RS was evaluated using X-ray diffraction. A total of 60 trials were conducted. Data preprocessing, including normalization and removal of outliers, was executed before constructing the ML algorithm, leaving 59 valid tests for model training and testing. Separate datasets for training (70 % of the data) and testing (30 %) were randomly selected from the valid experimental tests. PCA enhanced the RBFN model’s generalization by reducing data dimensionality and providing the hidden units parameter. The eigenvectors obtained through PCA served as an efficient initial reference for RBF centroids, highlighting principal directions of variation. The PCA-RBFN model, using a multiquadric radial function, exhibited robust performance in capturing underlying patterns during training and demonstrated balanced results in the tests. In the PCA-RBFN model training stage, it exhibited a coefficient of determination (R2) of 76.66 %, a mean average error (MAE) of 72.15 MPa, and a root mean square error (RMSE) of 84.94 MPa. In the testing stage, the model showed increased metrics, indicating its ability to predict RS values accurately, with an R2 of 80.54 %, MAE of 51.25 MPa, and RMSE of 70.36 MPa. The evaluation between the training and testing stages highlighted the model’s coherence in performance, demonstrating its ability to generalize well to new data. A second comparative analysis was conducted with a conventional RBFN approach using stochastic method for centroid determination. The hybrid PCA-RBFN method exhibited lower computational effort, requiring only three iterations compared to 221,923 iterations in the conventional approach. Despite the conventional approach yielding better metrics in the training stage, it exhibited signs of overfitting, a common concern in machine learning models. The hybrid PCA-RBFN consistently outperformed it regarding generalization and fit during testing. The proposed methodology holds practical implications for the manufacturing industry, allowing the integration of a pre-trained predictive model into machine controllers or smart sensors. The hybrid PCA-RBFN’s computationally lightweight approach also supports incorporating real-time adaptive algorithms into production systems, enabling continuous real-time adjustments to the model factors and weights, thereby improving automated control.

On straightness measurements of large CNC machine tools

The CNC (computerized numerically controlled) machines are widespread in use due to their high capability of precise manufacturing in industrial production. They have a wide range of designs depending on the working capacity in manufacturing. The associated form errors in large-capacity CNC machines during production shall be identified and corrected or eliminated. This study presents an investigation of one of the main form errors that may affect the manufacturing precision of these machines. This error type is a straightness error with both two kinds of horizontal and vertical errors. The study is carried out for a vertical turning center CNC machine type. The straightness errors are measured for the X axis at different latches in the Z direction and for the Z axis at three positions in the X direction with multi-displacement steps. Different algorithms are used in the determination of straightness errors. The X-axis has minimum horizontal straightness errors at latch Nr. 3 and minimum vertical straightness errors at latch Nr. 5. For the Z axis, the minimum values for horizontal and vertical straightness errors exist when the spindle is located 1200 mm away from the machining center to the right. The displacement steps have a significant impact on the determination of straightness errors.

Investigating Twist Drill Design Influence on Thrust Force and Surface Roughness in Drilling AFRP/ Al7075-T6 Stacks Materials

Drilling Aramid Fiber-Reinforced Plastic (AFRP) presents unique challenges when compared to drilling other composite panels. These difficulties arise from the high-toughness characteristics of aramid fibers, which exhibit a tendency for ductile deformation during the drilling process. This research explores the influence of drill bit design on the drilling process stack-up materials, which comprise Aramid Fiber Reinforced Plastic Composite Laminates (AFRP) and Aluminum Al7075-T6. Three distinct bit designs were employed in the experiment, conducted on a Computer Numerical Control (CNC) machine operating at a spindle speed of 2000 rev/min and a feed rate of 0.05 mm/rev. To measure thrust force during drilling, a dynamometer was integrated into the setup. Subsequently, a roughness tester was utilized to assess the hole surface roughness of the stack-up materials. For AFRP materials, the w-point drill design emerged as the optimal choice, reducing thrust force by approximately 5% to 13% compared to other drill bit designs. Conversely, for Al7075-T6 panels, the tapered web drill design demonstrated exceptional results, lowering thrust force by approximately 21% and 50% in comparison to burnishing and w-point drill bits, respectively. In terms of hole surface roughness, the burnishing drill type consistently produced the smoothest surfaces, boasting significant improvements of 44% and 82% when compared to the tapered web and w-point drill bits for AFRP panels. Similarly, for Al7075-T6 panels, the burnishing drill type consistently outperformed the tapered web and w-point drill bits by 74% and 88%, respectively, in achieving a superior hole surface finish. These findings underscore the critical importance of selecting the appropriate drill bit design to optimize thrust force reduction and hole surface quality when working with stack-up materials.

Precision prediction in grinding processes based on displacement signal conversion into recurrent plot

The processing of grinding data and the prediction of accuracy are extremely complex; this paper proposes a novel prediction method to ensure the machining accuracy of computer numerical control (CNC) grinding machines. It consists of two components, namely the filter decomposition recurrence plot (RP) transformation (FDRP) and the deep inverted residual attention network (DIRAN). A pipeline named FDRP has been designed to address the issues in the processing of data and the shortcomings of RP. Firstly, the displacement signals undergo filtering to preserve essential grinding information while effectively removing noise. Secondly, long-time series signals are decomposed and augmented based on the characteristics of the machining process. Lastly, an RP transformation is applied to one-dimensional time series data, resulting in the generation of images that accurately represent the grinding process. Furthermore, this paper proposes a novel machining accuracy prediction model. The DIRAN uses a multi-layer inverse residual network structure combined with attention mechanism to extract the features of two-dimensional RP, and its performance is better than other typical prediction methods. It can be applied to predict the polar angle of the workpiece in industrial processing and reduce the defect rate.

Optimization of machining path for integral impeller side milling based on SA-PSO fusion algorithm in CNC machine tools

The five axis linkage Computer Numerical Control machine tool for integral impeller can achieve blade machining through side milling, which is of great significance for improving the machining accuracy, production efficiency, and long-term stability of integral impeller blades. This study is based on non-uniform rational B-spline curves and aims to reduce the surface over cutting or under cutting of integral turbine blades. The path planning of non deployable ruled surfaces was analyzed in depth through side milling, and the path planning model of the side milling cutter axis was solved through a fusion algorithm of simulated annealing algorithm and particle swarm optimization algorithm, in order to find the optimal path through iterative process. As the number of iterations increased, the error values of particle swarm optimization algorithm and simulated annealing particle swarm optimization fusion algorithm gradually decreased, with convergence times of about 7 and 6, respectively. The stable error value of the fusion algorithm was 0.253, which is 30.45% lower than that of the particle swarm optimization algorithm. The optimal number of iterations for solving the model using particle swarm optimization algorithm and fusion algorithm was the 7th, with range values of 0.0213 and 0.0165 mm, respectively. The tool axis trajectory surface optimized by the fusion algorithm was closer to the tool axis motion state compared to the initial tool axis trajectory surface. The range of the sum of mean squared deviations for single and global cutting was 0.0011–0.0198 and 0.046–0.0341, but the overall error value was relatively small. This study effectively reduces the envelope error of machining tools and improves machining accuracy, thereby solving the principle error of non expandable ruled surfaces in the motion trajectory of the blade axis of the integral turbine. This provides new research ideas for the intelligent development of Computer Numerical Control machining technology.