Dynamic parameters are crucial in designing robotics systems because they reflect an actual robot. Conventional identification methods require that the robot execute the optimal motion; however, they spend time trying all possible trajectories in the robot. This article shows the identification of a robot arm of 2 degree-of-freedom with an algorithm based on a convolutional neural network (CNN) and their dynamic model. The proposal consists of a CNN that uses an image construct with a proposed conversion technique and the robot signals. The algorithm gets the parametric residuals from this signal image to find the parameters without trajectory optimization. An embedded system on a Field Programmable Gate Array (FPGA) has the classical controller Proportional-Derivative to execute a predefined trajectory for the identification. The identified parameters and the predefined motion rebuild the torque with the dynamic model. A proposed evaluation metric based on the discrete cosine transform evaluates the similarity of the actual and reconstructed torques. Four numeric tests verify the algorithm by torques created with the dynamic model, the predefined trajectory, and a parameter set. The similarity of numeric torques and their rebuilding overcomes 97.38%, and the experimental and rebuilt torque with the identified parameters is over 93.55%. The proposed algorithm is compared with least-squares, and the results show that the proposed method provides better identification of the experimental robot.

Las redes neuronales artificiales son útiles para procesar datos con información incompleta para obtener una salida deseada. En los sistemas de medición de robots manipuladores, solo se toman muestras cuantificadas de la posición y, por lo tanto, no se puede ejecutar en un tiempo razonable algoritmos deterministas para extraer los parámetros del robot. En el estado del arte, se abordan algoritmos de extracción de parámetros basados en la suposición de que no existe la cuantificación de las señales del movimiento del robot y que la primera y segunda derivada de la posición son muestreadas y no estimadas. En este trabajo, se propone un algoritmo basado en una red neuronal entrenada para extraer los parámetros de un determinado robot para reducir el tiempo de caracterización del robot, además, con la metodología propuesta se pueden extraer parámetros dinámicos del mismo tipo de robot con el que se ha entrenado la red neuronal.

This article presents a software platform (SP) that helps generate convolutional and feed-forward neural networks and a parametric identification algorithm is proposed for a Cartesian robot using convolutional neural networks (CNN) generated and trained with the proposed SP. The user interface is friendly and aids in developing convolutional and feed-forward neural networks. The SP is made in LabVIEW®. The user does not need the complete knowledge of mathematics used to perform the training or execution of the network or the programming skills to perform the code that performs such tasks. The SP is designed to reduce the deployment time of neural networks, providing the user with a graphical interface that guides the user through the formation and development of the neural network, this is one of the main contributions. The SP interface is described in this article, showing all the options offered. Five neural networks are presented to prove and demonstrate the software platform’s use. The dynamic models of the Cartesian robot are used; one has six parameters and the other ten parameters. The maximum similarity achieved by the identification algorithm with the six-parameter dynamic model was 99.15% and 99.92% for the ten-parameter model; both are numerical torque analyses. A real Cartesian robot was identified, and five experimental torques were reconstructed for each axis; the maximum similarity was 97.87%. The proposed algorithm is compared with least squares, which obtain 95.81%. Therefore, the results show that the proposed method generates better parametric identification.

In this article, we present a system to measure current in the range of 0 to 10 $\mathsf{\mu }$A with high-voltage isolation up to 5 kV. This current monitor consists of three ammeters connected in series, to improve the resolution in the measurement. The design features several innovative elements such as using low voltage to provide power to the devices to measure the current and digitize it with a sampling frequency of 1 KHz, it is generated based on a DC-DC converter that produces three voltages, +12 V, −12 V, and 5 V, from a conventional 10 V source. The three voltages are referenced to the same floating ground. The DC-DC converter has a high voltage insulation up to 5 kV and four optocouplers with an insulation up to 20 kV are used to read the digitized data. The introduction of a DC-DC converter contributed to reduce the noise level in the analog part of the circuit which has been resolved implementing shields inside the board. In particle physics, several systems are used to detect particles in high-energy physics experiments such as Gas Electron Multiplier (GEM), micromegas, etc. GEMs suffer small deteriorations due to discharges in constant operation and require monitoring the current consumption at high frequency (1 kHz). In this work, we present the design and operation of a 0 to 10 $\mathsf{\mu }$A auto scale ammeter. The results obtained by monitoring the current in a 10 × 10 cm${}^2$ GEM are shown.

En el presente trabajo se muestra el diseño de un sistema mecatrónico, el cual emula los movimientos del cuello humano, ya que sostendrá la cabeza de un robot humanoide (Arthur) desarrollado por la empresa Hanson Robotics. El diseño mecánico se basa en un robot esférico de 3 grados de libertad (3-GDL), se desarrolla el modelo dinámico a través de las ecuaciones de movimiento de Euler-Lagrange. La etapa de control es una tarjeta de desarrollo FPGA (arreglos de compuertas programables en campo) de la familia Cyclone IV, la etapa de potencia se basa en transistores BJT, se implementa el controlador Tangente hiperbólico y una interfaz de comunicación WiFi para configurar el robot desde una PC con ayuda del software Labview. Como resultado se muestra la integración del sistema mecatrónico, la interfaz desarrollada junto con la comunicación FPGA-PC y control de posición. El trabajo futuro será la implementación del sistema en el robot humanoide.