Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 3

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: robot calibration

Sortuj według:

Ogranicz wyniki do:

Hyperparameter optimization of artificial neural networks to improve the positional accuracy of industrial robots

Uhlmann Eckart, Polte Mitchel, Blumberg Julian, Li Zhoulong, Kraft Adrian

Journal of Machine Engineering

2021

Vol. 21, No. 2

47--59

Due to the rising demand for individualized product specifications and short product innovation cycles, industrial robots gain increasing attention for machining operations as milling and forming. Limitations in their absolute positional accuracy are addressed by enhanced modelling and calibration techniques. However, the resulting absolute positional accuracy stays in a range still not feasible for general purpose milling and forming tolerances. Improvements of the model accuracy demand complex, often not accessible system knowledge on the expense of realtime capability. This article presents a new approach using artificial neural networks to enhance positional accuracy of industrial robots. A hyperparameter optimization is applied, to overcome the downside of choosing an appropriate artificial neural network structure and training strategy in a trial and error procedure. The effectiveness of the method is validated with a heavy-duty industrial robot. It is demonstrated that artificial neural networks with suitable hyperparameters outperform a kinematic model with calibrated geometric parameters.

On the improvement of calibration accuracy of parallel robots – modeling and optimization

Bentaleb Toufik, Iqbal Jamshed

Journal of Theoretical and Applied Mechanics

2020

Vol. 58 nr 1

261--272

This paper proposes kinematic based calibration methods for Delta parallel robots. The boundary of the robot workspace is computed using a forward kinematic model. Influence of errors in kinematic parameters on the workspace boundaries is investigated. The novelty of the proposed approach lies in Jacobian-based computation of kinematic models. Also, the present work extends and applies the existing calibration methods traditionally meant for serial robots on the Delta robot. These methods include the forward method and the inverse method. Simulation results confirm the efficacy of the proposed calibration strategies.

Rotation error modeling and identification for Robot kinematic calibration by circle point method

Santolaria J., Conte J., Pueo M., Javierre C.

Metrology and Measurement Systems

2014

Vol. 21, nr 1

85--98

Screw axis measurement methods obtain a precise identification of the physical reality of the industrial robots’ geometry. However, these methods are in a clear disadvantage compared to mathematical optimisation processes for kinematical parameters. That’s because mathematical processes obtain kinematical parameters which best reduce the robot errors, despite not necessarily representing the real geometry of the robot. This paper takes the next step at the identification of a robot’s movement from the identification of its real kinematical parameters for the later study of every articulation’s rotation. We then obtain a combination of real kinematic and dynamic parameters which describe the robot’s movement, improving its precision with a physical understanding of the errors.