Real-time Thermal Error Compensation Research Articles

Real-time Thermal Error Compensation of Machine Tools Based on Machine Learning Model and Actual Cutting Measurement via Temperature Sensors

Real-time Thermal Error Compensation of Machine Tools Based on Machine Learning Model and Actual Cutting Measurement via Temperature Sensors

Novel Real-Time Compensation Method for Machine Tool’s Ball Screw Thermal Error

The real-time compensation of thermal error in ball screws is an effective means to improve the accuracy of machining tools. However, the trade-off between robustness and computational efficiency of existing ball screw thermal error models is complicated and not conducive to practical, high-precision, real-time error compensation. Focusing on this problem, we propose an iterative prediction model of screw thermal error based on a finite difference equation. By assuming an approximately linear relationship between heat generation and the ball screw’s convection power and feed speed, a simplified and more efficient identification of physical parameters needed for the iterative model is achieved. The proposed method is integrated with a three-axis drilling and tapping machine powered by an HNC–848D controller. A test piece machine using the proposed real-time thermal error compensation method exhibited a maximum machining error of 13 µm, compared to the 71 µm of an uncompensated specimen. The proposed method is demonstrated to improve machining accuracy, especially in the X- and Y- axes, and overcome the limitations of traditional thermal error prediction models.

Real-time Thermal Error Compensation Strategy for Precision Machine tools

Abstract Present manufacturing trend is towards producing precision components with better accuracy. Machine errors like geometrical, thermal and process errors affect the component accuracy. Among these errors, thermal error contributes more than 50-60% of the total machining error. This paper mainly focuses on the development of a real-time thermal error compensation module for precision machine tools and talks about effective modeling of thermal errors, development of thermal error compensation model using feed-forward backpropagation neural network and also simplified model using regression analysis technique, algorithm development for real-time compensation and implementation of module onto the open architecture CNC controller. The developed module has been successfully tested on a Diamond Turning Machine (DTM) by machining the precision component and also verified the effectiveness of the module

Thermal characteristics testing and thermal error modeling on a worm gear grinding machine considering cutting fluid thermal effect

The coolant absorbing cutting heat has strong influence on thermal behaviors for high precision machine tool using flood cooling technique. However, the majority of applied thermal error compensation models are without considering cutting fluid thermal effect, which results in poor simulation accuracy of thermal deformation. This paper experimentally investigated the effect of coolant temperature on the thermal characteristics of a worm gear precision grinding machine. Experiments were carried out under three conditions: no-load with coolant, no-load with heated coolant, and load test. Moreover, a real-time thermal error compensation model was theoretically developed and validated based on the experimental data involving the cutting fluid thermal effect. The results show that the temperature distribution of the machine tool was more uniform and the temperature gradient was decreased when the grinding heat was partially considered using heated coolant, which indicates that coolant can positively affect the thermal behavior if it is controlled to flow correctly. The thermal error compensation model was built based on the optimal four temperature variables and with a high accurate prediction and robustness. For the no-load operating conditions, the maximum absolute errors and mean absolute errors are 2.7 μm and 1.5 μm respectively. For the load operating conditions, the prediction accuracy of the model built by no-load measuring data is also greatly improved because the grinding heat is partially considered by heated coolant in the no-load test. And the maximum prediction error is 13.0% when the influence of the feed drive system adjustment is considered.

Thermal error modeling and compensation of a heavy gantry-type machine tool and its verification in machining

In order to derive a thermal error model that can better reflect the physical model of the machine tool to improve the model’s robustness and also has an explicit and simpler expression for real-time thermal error compensation, a new thermal error model of a heavy gantry-type machine tool was established. Firstly, multi-body system (MBS) was used to transform the thermal error modeling of the machine tool into the thermal error modeling of the discrete parts of the machine tool. Then, as for the thermal error modeling of the slider-ram structure, by analyzing the characteristic of the thermal expansion of a one-dimensional rod, power function was considered to better reflect that relationship in which the index number can represent the distance between heat source and the temperature measurement location. Then, its thermal error model was expressed as the superposition of two power functions according to the thermal superposition principle and the distribution of the heat sources. As for the thermal error modeling of gantry structure, it was simplified to a frame with −3 DOF. And its thermal error model was derived by virtual work principle (VWP). Then, the whole thermal error model of the machine tool was embedded into the Simens840d NC system and S7-300 programmable logic controller to establish a thermal error compensation system. Finally, the error model and compensation was verified by machining a rhombus-shaped workpiece of which different zones reflect the thermal error in different directions. And the workpiece was measured by a CMM. The results show that the average thermal error can be reduced from around 101 to 13.5 μm after the compensation, indicating the effectiveness of the thermal error modeling and compensation for the practical application.

Thermal error compensation based on genetic algorithm and artificial neural network of the shaft in the high-speed spindle system

To improve the accuracy, generality and convergence of thermal error compensation model based on traditional neural networks, a genetic algorithm was proposed to optimize the number of the nodes in the hidden layer, the weights and the thresholds of the traditional neural network by considering the shortcomings of the traditional neural networks which converged slowly and was easy to fall into local minima. Subsequently, the grey cluster grouping and statistical correlation analysis were proposed to group temperature variables and select thermal sensitive points. Then, the thermal error models of the high-speed spindle system were proposed based on the back propagation and genetic algorithm–back propagation neural networks with practical thermal error sample data. Moreover, thermal error compensation equations of three directions and compensation strategy were presented, considering thermal elongation and radial tilt angles. Finally, the real-time thermal error compensation was implemented on the jig borer’s high-speed spindle system. The results showed that genetic algorithm–back propagation models showed its effectiveness in quickly solving the global minimum searching problem with perfect convergence and robustness under different working conditions. In addition, the spindle thermal error compensation method based on the genetic algorithm–back propagation neural network can improve the jig borer’s machining accuracy effectively. The results of thermal error compensation showed that the axial accuracy was improved by 85% after error compensation, and the axial maximum error decreased from 39 to 3.6 µm. Moreover, the X/ Y-direction accuracy can reach up to 82% and 85%, respectively, which demonstrated the effectiveness of the proposed methodology of measuring, modeling and compensating.

Study on a novel thermal error compensation system for high-precision ball screw feed drive (2nd report: Experimental verification)

Real-time thermal error compensation of machine tool feed drive in general can be separated into three steps such as modeling, measurement and compensation. In the previous report, as the parts of the thermal error compensation system, component heat generation, compensation method, thermal model, mathematic model and calculation method were studied respectively. And a series of simulations was carried out in several kinds of working condition. And then, in order to discuss the correctness of the developed ball screw thermal error compensation system, a series of tests contains axial deformation, positioning accuracy, temperature variation and temperature distribution was carried out in the same working condition of prediction. As the results, the test data well confirmed the correctness of the developed ball screw thermal error compensation system.

Real-time thermal error compensation method for robotic visual inspection system

The thermally induced error is a critical element in the total errors for the robotic visual inspection system during its long-term operation. This paper investigates the thermal behavior of the robotic visual inspection system and proposes a real-time thermal error compensation method. Based on the fixed-point constraint, an error calibration model is derived by associating the thermally induced parameter errors with the deviations in the measured coordinates of the fixed reference point during the robot warm up and cool down. A joint-by-joint test is performed to investigate the link parameters that change significantly with respect to temperature variations. Standard spheres are adopted as the calibration targets, and optimum projected angles for sphere center measurement by visual sensor are obtained based on theoretical analysis and experimental data. Contrary to most other works, the method needs no exact knowledge of the temperature sensors and is well suited for online dynamic thermal error compensation for the robotic visual inspection system. Verification experiment is carried out on a car-body assembly line, and results show that the max/mean residual error for the tested points has been reduced from 0.441/0.195 to 0.136/0.078 mm with the significant parameters calibrated.

A New Prediction Model for Thermally Induced Errors of a Turning Center

Thermally induced errors and geometric errors are two main sources that affect the machine tool accuracy when machining. In the last decade, real time compensation method had received wide attention for its ability to reduce the thermal error cost–effectively. Although real-time thermal error compensation techniques have been successfully demonstrated in laboratories, several difficulties hinder its widespread application. The selection of temperature variables and the setup of the error measurement system are the most critical ones among these difficulties. In this paper, a new on line measurement system and a new model that predicts the thermal error of a turning center are developed. The on-line measurement system using a Renishaw’s LT02S probe system is capable of measuring thermal error of a CNC turning center in real cutting conditions. The neural network uses the cutting conditions as the mapping inputs to avoid problems occurred in the traditional temperature-error mapping model. Results show the proposed measurement system and prediction model can be used to accurately estimate the thermally induced error in real cutting conditions.

Real-time Thermal Error Compensation Module for Intelligent Ultra Precision Turning Machine (iUPTM)

Accuracy & precision are 1he main requirements for ultra precision machine tools. Many factors affect 1he performance of 1he system 1hat in turns affect 1he product quality. Among all sources of errors, the thermo mechanical deformation errors are the main contributor for 1he overall geometrical errors. This paper mainly aims at establislunent of methodology to compensate thermal deformation errors in real-time for ultra precision machine tools. The real-time thermal error compensation module has been developed and integrated to intelligent Ultra Precision Turning machine. The module includes temperatures as inputs, neural network algorithm for computing the thermal deformations errors, ‘C’ programming for real-time calculations and integration with open architecture CNC controller. The module runs in silent mode which avoids human intervention for correction of thermal deformation errors.

Research on Thermal Error Compensation Instrument Based on Thermal Modal Analysis for NC Machine Tools

Great efforts have been made to improve the accuracy of NC machine tools, within which thermal error compensation is one of the most efficient ways. A new thermal error compensation instrument which is based on thermal modal analysis for NC machine tools is introduced in this paper. OMRONsCJ2M-CPU11 is used as microcontroller, and SAILING TECHNOLOGYs STA-A08 temperature measuring modules as temperature transmitter. Through hardware and software design, high precision and stability can be achieved. By measuring several key points temperature and making use of a thermal error compensation theory, real-time thermal error compensation can be output to the machine tool, thus thermal error can be reduced.

An Integrated Modeling Approach for ANN-Based Real-Time Thermal Error Compensation on a CNC Turning Center

Thermally induced errors play a critical role in controlling the level of machining accuracy. They can represent a significant proportion of dimensional errors in produced parts. Since thermal errors cannot totally be eliminated at the design stage, active errors compensation appears to be the most economical and realistic solution. Accurate and efficient modeling of the thermally induced errors is an indispensable part of the error compensation process. This paper presents an integrated and comprehensive modeling approach for real-time thermal error compensation. The modeling process is based on multiple temperature measurements, Taguchi’s orthogonal arrays, artificial neural networks and various statistical tools to provide cost effective selection of appropriate temperature variables and modeling conditions as well as to achieve robust and accurate thermal error models. The experimental results on a CNC turning center confirm the feasibility and efficiency of the proposed approach and show that the resultant model can accurately predict the time-variant spindle thermal drift errors under various operating conditions. After compensation, the thermally induced spindle errors were reduced from 19m to less than 1 m. The proposed modeling optimization strategy can be effectively and advantageously used for real-time error compensation since it presents the benefit of straightforward application, reduced modeling time and uncertainty.

A Comprehensive Approach for Thermal Error Model Optimization for ANN-Based Real-Time Error Compensation in CNC Machine Tools

Thermally induced errors play a critical role in the control of machining accuracy. They can account for as much as 70% of dimensional errors in produced parts. Since thermal errors cannot totally be eliminated at the design phase, errors compensation appears to be the most economical solution. Accurate and efficient modeling of the thermally induced errors is an essential part of the error compensation process. This paper presents a comprehensive approach for thermal error modeling optimization. The proposed optimization method is based on multiple temperature measurements, Taguchi’s orthogonal arrays, various statistical tools and artificial neural networks to provide cost effective selection of appropriate temperature variables and modeling conditions as well as to achieve robust and accurate thermal error models. The proposed approach can be effectively and advantageously used for real-time thermal error compensation since it presents the benefit of straightforward application, reduced modeling time and uncertainty. The experimental results on a CNC turning center confirm the feasibility and efficiency of the proposed optimization method and show that the resultant model can accurately predict the time-variant thermal error components under various operating conditions.

Real-time compensatory control of thermal errors for high-speed machine tools

This paper proposes a developmental procedure of a real-time thermal error compensator for a high-speed machine tool (HSMT). A vertical-type HSMT having a slant column with lightweight moving slides is used to investigate thermal characteristics. Since spindle speed is very fast in the HSMT, a large amount of thermal drift error occurs within a few minutes of operation. Owing to tooling problems of the high-speed spindle, axial offset errors also appear on the machined surfaces. If-then rules and thermal mode approaches are applied to remove defects of the machined surfaces. An infinite impulse response filter is used to compensate for surface roughness of the machine surface. A personal-computer-based error compensation scheme has been developed for the real-time thermal error compensation. Compensation interval of the developed compensator is selected to satisfy correction requirement of thermal errors of the HSMT. Experimental results confirm the validity of the developed compensator and show that the accuracy of machined surface is dramatically improved.

Neural network-based modelling and error compensation of thermally-induced spindle errors

This research is concerned with enhancing the accuracy of a machining centre by compensating for thermally induced spindle errors in real-time. A neural network model was developed for on-line thermal error monitoring. A PC-based error compensation scheme was also developed to upgrade a commercial CNC controller for real-time thermal error compensation without any hardware modifications to the machine. The spindle thermal errors of a vertical machining centre were reduced by 70% after compensation.

Quick testing and modeling of thermally-induced errors of CNC machine tools

This research is concerned with enhancing the accuracy of a machining center through compensating for the thermally induced errors of the spindle and leadscrews using software. A quick set-up and multiple degree of freedom measurement system consisting of an on-machine probe and artifacts has been developed to accelerate and simplify the thermal error measurement. An artificial neural network based technique which correlates the thermal error field to the machine temperature field is then developed to model the measured multiple thermal errors all together. Test results show that the ANN can not only fit the highly nonlinear thermal errors well, but has also predicted thermal errors well even under varying or new cutting conditions with a precision of more than 85%. A PC based error compensation scheme has also been developed to upgrade a FANUC CNC controller for real-time thermal error compensation. Test results on a vertical machining center show that a 70–90% reduction of thermal errors has been gained after compensation.