Neural network contour error predictor in CNC control systems

Erwiński, Krystian; Paprocki, Marcin; Wawrzak, A.; Grzesiak, Lech M.

doi:10.1109/mmar.2016.7575193

Cited by 19 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1) different neural network features: We consider the proposed feature and others in the literature, including: i) reference velocities at the current instant and at the previous instants [28]; ii) reference position, velocity, and acceleration at the current instant [22]; iii) reference velocities at the current instant, at the previous and at the next instants, and the non-linear features (proposed). The comparative results for a butterfly curve are given in Fig.…”

Section: B Comparison Of Different Neural Network Features and Differ...mentioning

confidence: 99%

Prediction and Compensation of Contour Error of CNC Systems Based on LSTM Neural-Network

et al. 2022

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

show abstract

Section: B Comparison Of Different Neural Network Features and Differ...mentioning

confidence: 99%

Prediction and Compensation of Contour Error of CNC Systems Based on LSTM Neural-Network

et al. 2022

IEEE/ASME Trans. Mechatron.

View full text Add to dashboard Cite

show abstract

“…It is mainly caused by servo dynamics, thermal strains, data losses and other external disturbances, etc. [9]. A typical servo system consists of three feedback loops, which are current-, speed-and position-loop.…”

Section: Introductionmentioning

confidence: 99%

A Feedrate Planning Method in CNC System Based on Servo Response Error Model

et al. 2023

View full text Add to dashboard Cite

Reducing servo response error and further making reduction on contour error is crucial for high-precision computer numerical control (CNC) machine tools. For a permanent magnet synchronous motor (PMSM) servo system, there is always a response lag in feedrate tracking, which would introduce response error into the machining trajectory. Therefore, it is necessary to improve the performance of feedrate planning and interpolation for trajectory path. In this paper, a novel contour error compensation strategy is proposed. Compared with the mainstream methods, the proposed method offers a simplified alternative to existing contour error estimation techniques. Through a three-closed-loop control structure of a PMSM servo system, a response error model is founded. Afterwards, an improved S-model feedrate planning method is introduced according to the servo response error compensation. This predicted error is subsequently compensated in each interpolation cycle, resulting in a reduction of contour error. Finally, simulations and experiments are performed to demonstrate that the contour error can be reduced in both the ‘∞’-shaped Non-Uniform Rational B-Spline (NURBS) curve path and the butterfly-shaped NURBS curve path using the proposed method.

show abstract

“…VS are often used in chemical industry [13] but also in mechanical engineering [14]. Other approaches combine the virtual sensor approach with AI algorithms [15,16]. However, in this case a large number of high-quality data sets for the training of the AI models (e.g., neuronal networks) is necessary.…”

Section: Introductionmentioning

confidence: 99%

Virtual Sensor for Accuracy Monitoring in CNC Machines

Doerrer¹,

Otto²,

Kolouch³

et al. 2022

JMMP

View full text Add to dashboard Cite

Vibrations are limiting the productivity and the process quality of cutting machine tools. For the monitoring of these vibrations, often external sensors, such as acceleration sensors, are used. These external systems require additional cost and maintenance effort. This paper presents a virtual sensor, which is capable of detecting vibrations at the tool center point, based on internal machine data. External sensors are only necessary once for model identification. This reduces the overall cost of the system significantly. The virtual sensor uses the high-quality data of the linear position encoder near the ball screw nut and calculates the vibrations at the tool tip by using transmissibility functions. This paper explains the theory behind the used transmissibility functions and describes how they are measured, by comparing different experimental approaches to identify the modal parameters of cutting machine tools. After the identification of the sensor, a dynamical test cycle is used to prove the physical correctness.

show abstract

Neural network contour error predictor in CNC control systems

Cited by 19 publications

References 23 publications

Prediction and Compensation of Contour Error of CNC Systems Based on LSTM Neural-Network

Prediction and Compensation of Contour Error of CNC Systems Based on LSTM Neural-Network

A Feedrate Planning Method in CNC System Based on Servo Response Error Model

Virtual Sensor for Accuracy Monitoring in CNC Machines

Contact Info

Product

Resources

About