5-axis Machine Tool Research Articles

AI-based inspection of the axes of machine tools

AI-based inspection of the axes of machine tools

Accurate prediction of five-axis machining cycle times with deep neural networks using Bi-LSTM

This paper presents a novel machine learning (ML) based approach to predict machining cycle (part program running) times for complex 5-axis machining. Typical 5-axis machining toolpaths consist of short-segmented discrete linear cutter location lines (CL-lines) with simultaneously varying tool center point (TCP) and orientation vectors (ORI). As the 5-axis machine tool NC (numerical control) system tries to interpolate such part programs smoothly, the TCP motion decelerates and accelerates repeatedly causing the actual feedrate to fluctuate. The actual observed (resultant) feedrate can be approximately 30 % lower than the user commanded one. Furthermore, if the toolpath requires the 5-axis machine tool to travel closer to its singular point, or if the workpiece placement on the table is not optimal, actual feedrate is even lowered further. This paper presents two ML-based approaches to accurately predict 5-axis machining toolpaths. The first strategy uses a bidirectional long short-term memory (Bi-LSTM) network to model the machine tool behavior and generates a direct final cycle time estimation for any given part program. This approach only uses the toolpath geometry to predict the cycle time, and for training it only needs the “final” cycle times of similar part programs making it practical on today’s shop floors. The second strategy requires individual CL-line processing times for training. In return, it can provide highly accurate cycle time predictions. Both strategies can capture the interpolation dynamics of 5-axis machine tool NC systems accurately. Simulation studies and experimental validations are conducted on modern 5-axis machine tools with varying workpiece placements and interpolation parameters. Proposed approaches have shown to predict cycle times with 90–95 % accuracy on real-life complex 5-axis machining toolpaths.

Promoting Machining Efficiency of 5-Axis Machine Tools with Non-Contact On-Machine Measurement Function

Promoting Machining Efficiency of 5-Axis Machine Tools with Non-Contact On-Machine Measurement Function

Industrial IoT system for laser-wire direct energy deposition: data collection and visualization of manufacturing process signals

Industry 4.0, also known as the Fourth Industrial Revolution, is a term used to describe the current trend of automation and data exchange in manufacturing and other industries. The Internet of Things (IoT) plays a crucial role in Industry 4.0 by connecting devices, machines, and products to the Internet and enabling real-time data exchange. Moreover, additive manufacturing is a key developing manufacturing technology in Industry 4.0. New technologies such as data analysis with Artificial Intelligence and machine vision are widely used in optimization. However, in a lab environment, these technologies depend on the data collected from the process. For such work, the researchers should be able to focus on their core research rather than on the development of infrastructure to collect and analyse the data. This research presents an open software and hardware IoT solution to monitor a laser wire direct energy deposition system installed in a cartesian type 3-axis machine tool. The IoT solution adopts three open-source tools for core issues, such as 1) interoperability, flexibility, and availability; 2) data storage; and 3) data visualization of sensor data and manufacturing process signals. The system architecture is based on one or more edge devices connected to sensors and forwarding their data toward a local API endpoint. The endpoint is created with Node-RED, an open-source visual flow-based development tool for IoT data. Node-RED forwards the data to an open-source InfluxDB database. Finally, the data is visualized with an open-source Grafana application. The system is prototyped, designed, implemented, and tested in a lab environment to monitor a laser-wire direct energy deposition process. The significance of such a flexible IoT data collection system for research and development projects can be integral. Thus, providing savings in time and money can substantially speed up the development of new technologies where the value arises from the sensor data and its analysis.

Calibration of link errors in rotary axes of five-axis machine tools using a six-dimensional motion measuring device

In this study, the position-independent geometric errors (PIGEs) of five-axis machine tools are identified and calibrated using a Stewart–Gough platform (SGP) based Motion Measuring Device (MMD). As the MMD of micrometer-level accuracy is cable of six-dimensional pose measurements, a closed kinematic chain is established by installing the upper and lower plate of the MMD to the spindle and rotary worktable of the machine tool, respectively. Particularly, the sensor-mounting misalignments, which are inevitable but mostly ignored in the previous PIGE identification methods, are formulated and identified together with the PIGEs. Thus, the sensor-mounting misalignments will not affect the accuracy of PIGE calibration. The proposed method is verified by simulation and experimental results. The synchronous motion test (SMT) demonstrates that the five-axis machine tool owns a high accuracy of 5 micrometers in the tested motion range after PIGE calibration.

Comprehensive analysis and evaluation of the geometric errors of the rotating axis of five-axis double-pendulum machine tools based on S-shaped samples

Comprehensive analysis and evaluation of the geometric errors of the rotating axis of five-axis double-pendulum machine tools based on S-shaped samples

ESTIMATION OF MACHINE TOOL ACCURACY BASED ON MONTE CARLO SIMULATION USING MOVEMENT AXES GEOMETRIC ERRORS MODEL

Accuracy is one of the most important feature of a machine tool. Being able to estimate the overall accuracy of a machine tool represented by the total volumetric error can be a huge advantage in the design process. This paper provides overview of methods used for geometric error transfer modeling and volumetric error modeling. An error transfer rigid body model is derived and after that, a random linear guideway straightness error profile generator is proposed. This allows to simulate a movement axis with random straightness errors of rails and computed geometric errors of an assembled axis. Volumetric error of a 3-axis machine tool is then modeled using its kinematic scheme and homogenous transformation matrices with 21 kinematic errors. Using simulated axes as input to the volumetric model, an entire machine tool can be simulated. From that, the total volumetric error can be obtained and a Monte Carlo simulation carried out. This allows to analyze statistics of the total volumetric error and with slight input changes (rail straightness tolerance), a sensitivity analysis can be performed to determine the most influential errors in the machine tool.

Accurate Detection and Smoothness-Oriented Avoidance Method of Singularity in 5-Axis CNC Machining

As an inherent flaw in the kinematic chain mechanism of 5-axis machine tools, singularity can induce dramatic changes in machine axes motion and unfavorable fluctuations in feedrate. For effective singularity avoidance, it is desirable to first achieve accurate and efficient singularity detection and then eliminate the singularity without impairing tool orientation smoothness. This paper presents a novel approach for accurately detecting and smoothly avoiding the singularity in 5-axis CNC machining. In the detection method, two exclusion criteria are presented to efficiently exclude most non-singular segments of the tool orientation spline, and a curve intersection-based algorithm is thus developed to accurately identify the singular segments. In the singularity avoidance method, a concept of admissible tool orientation annulus (ATOA) is introduced, which serves to confine the range and magnitude of the tool orientation spline’s adjustments, and a local adjustment algorithm is then developed to enable the escape of the tool orientation from the singular region with controllable direction and deviation, while maintaining its continuity and smoothness. The effectiveness of singularity avoidance and the kinematic performance of the tool orientation modified by our method, are comparable to a state-of-the-art singularity avoidance algorithm. Finally, the conducted experiments validate the proposed method.

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.

Thermally compensated 5-axis machine tools evaluated with impeller machining tests

Thermally compensated 5-axis machine tools evaluated with impeller machining tests

A new effective decoupling method to identify the tracking errors of the motion axes of the five-axis machine tools

A new effective decoupling method to identify the tracking errors of the motion axes of the five-axis machine tools

Research on Machining Error Control Method Driven by Digital-twin Model of Dynamic Characteristics of Machining System

The position of each component structure in the machining space of the machining system directly affects the machining quality of the workpiece. In this paper, RBF neural network is used to study the spatial dynamic characteristics of the translational axes of five-axis CNC machine tools. It is the basis for building an evolvable knowledge base. Process evaluation, information feedback, and iterative optimization of thin-wall parts were carried out using digital-twin technology. Firstly, the model simulation of the translational machining space of a three-dimensional five-axis CNC machine tool is carried out by using the finite element method. The RBF neural network predicts the natural frequency of a translational machining space dynamic characteristics. It is further used to construct the dynamic characteristic spectrum of the translational space of CNC machine tools. Secondly, the machine tool flush space cutting process is built with a digital-twin system to optimize the iterative mechanism for machining process optimization. Finally, the method’s effectiveness was verified by experiments on milling thin-walled parts on a dual-turntable five-axis CNC machine and by contouring error measurement experiments. The results show that the average error of the optimized thin-wall contour is reduced by 26.9%. The iterative mechanism can continuously optimize the machining error and improve the machining accuracy. The iterative mechanism can continuously optimize the machining error and improve the machining accuracy.

Set Up for The Future

Manufacturing leader drives aerospace firm ASG TGM to double turnover after million-pound 5-axis machine tool investment

A Hybrid Approach for Predicting Critical Machining Conditions in Titanium Alloy Slot Milling Using Feature Selection and Binary Whale Optimization Algorithm

Monitoring the machining process is crucial for providing cost-effective, high-quality production and preventing unwanted accidents. This study aims to predict critical machining conditions related to surface roughness and tool breakage in titanium alloy slot milling. The Siemens SINUMERIK EDGE (SE) Box system collects signals from the spindle and axes of a CNC machine tool. In this study, features were extracted from signals in time, frequency, and time–frequency domains. The t-test and the binary whale optimization algorithm (BWOA) were applied to choose the best features and train the support vector machine (SVM) model with validation and training data. The SVM hyperparameters were optimized simultaneously with feature selection, and the model was tested with test data. The proposed model accurately predicted critical machining conditions for unbalanced datasets. The classification model indicates an average recall, precision, and accuracy of 80%, 86%, and 95%, respectively, when predicting workpiece quality and tool breakage.

Interoperable system for automated extraction and identification of machine control data in brownfield production

In recent years, Industrial Internet of Things (IIoT) respectively Industry 4.0 have become increasingly established and thus a widespread technology among companies. By means of data acquisition, processes can not only be made more sustainable and resource-efficient but through emerging technologies like fault detection or predictive maintenance, a higher Overall Equipment Effectiveness (OEE) can be achieved. As a result, the availability of the machine tools remains high and process chains will not be disturbed. However, many companies still operate in brownfield production sites with legacy machines and therefore with limited opportunities for machine data access and use in an economically viable manner. As a result, many advantages that would increase the OEE of machine tools cannot be used. To present a solution for retrofitting brownfield machines, a low-effort system was developed that extracts machine control signals from different machine data sources and automatically identifies them using a multi-stage algorithm. This algorithm consists of analytical rule bases built using expert knowledge and a machine learning model for classification. The best performing models were selected as machine learning models, which are a Residual Network, a Fully Convolutional Network, a Long-Short-Term Memory, and a Random Forest. With different datasets from two machine tools, the overall model was tested and was able to correctly identify the signals present with an accuracy of 86.92% to 98.93% on average. Using this approach, the identified signals are assigned to an information model linking them to the respective machine tool axes. As a result, brownfield machines are also made accessible for modern technologies such as predictive maintenance or a reduction in rejects as a result of error detection.

Simultaneous identification for geometric error of dual rotary axes in five-axis machine tools

For the rotary axes, the position-dependent geometric errors (PDGEs) and position-independent geometric errors (PIGEs) affect their rotational accuracy concurrently. Therefore, aiming at analyzing this coupling effect of geometric errors, a novel method is presented to identify the PDGEs and PIGEs of dual rotary axes simultaneously. The identification model is established based on the geometric error model and actual distances between the two retroreflectors, by which all geometric errors of two rotary axes can be obtained simultaneously. The identification results are validated by predicting volumetric errors, in which the deviations between the predicted and measured VEs are within 21.7 μm in three directions. Moreover, the root mean square error between the predicted and measured volumetric errors is 6.8 μm, which indicates that the proposed method can effectively accomplish the simultaneous identification of geometric errors. This identification method facilitates the further study of the coupling effect of PDGEs and PIGEs.

Application of machine learning for fleet-based condition monitoring of ball screw drives in machine tools

Ball screws are frequently used as drive elements in the feed axes of machine tools. The failure of ball screw drives is associated with high downtimes and costs for manufacturing companies, which harm competitiveness. Data-based monitoring approaches derive the ball screw condition based on sensor data in cases where no knowledge is available to derive a physical model-based approach. An essential criterion for selecting the condition assessment method is the availability of fault data. In the literature, fault patterns are often artificially created in an experimental test bench scenario. This paper presents ball screw drive monitoring approaches for machine tool fleets based on machine learning. First, the potentials of automated machine learning for supervised anomaly detection are investigated. It is shown that the AutoML tool Auto-Sklearn achieves a higher monitoring quality compared to literature approaches. However, fault data are often not available. Therefore, unified outlier scores are applied in a semi-supervised anomaly detection mode. The unified outlier score approach outperforms threshold-based approaches commonly used in industry. The considered data set originates from a machine tool fleet used in series production in the automotive industry collected over 8 months. Within the observation period, multiple ball screw failures are observed so that sensor data about the transient phases between normal and fault conditions is available.

An integrated trajectory smoothing method for lines and arcs mixed toolpath based on motion overlapping strategy

Smoothing the discretized toolpaths generated by CAM systems is vital for CNC options in improving the quality of machined surfaces. One discretized toolpath from CAM is commonly represented in the form of a series of linear and arc segments. The linear segment smoothing method has been extensively investigated. However, for linear and arc joint segments, which are in the form of G01 and G02/03 mixing modes, efficient smoothing strategies are still lacking. In this study, an integrated toolpath smoothing method based on motion overlapping strategy is proposed to improve the continuities of the mixture of G01 and G02/03 codes. To satisfy the requests of the kinematic limitations and high efficiency, heuristic algorithms are used to seek optimum kinematic parameters. Meanwhile, we also introduce a variable jerk-limited feedrate profile in the motion overlapping strategy to further reduce the machining time. Simulations on various toolpaths are performed to validate the effectiveness of the proposed method compared with the classical FIR and B-spline methods. The machining experiment executed on a 3-axis machine tool with a real-time CNC system also demonstrates the applicability of the proposed method.

Hierarchical design, dimensional synthesis, and prototype validation of a novel multi-spindle 5-axis machine tool for blisk machining

Hierarchical design, dimensional synthesis, and prototype validation of a novel multi-spindle 5-axis machine tool for blisk machining

Efficient compensation method of 5-axis machine tools based on a novel representation of the volumetric error

Efficient compensation method of 5-axis machine tools based on a novel representation of the volumetric error