DYNAMIC MODELING AND COMPENSATION METHOD BASED ON GENETIC NEURAL NETWORK FOR NEW TYPE ROBOT WRIST FORCE SENSOR

2006 ◽  
Vol 42 (12) ◽  
pp. 239 ◽  
Author(s):  
Along YU
Keyword(s):  
Neural Network ◽  
Dynamic Modeling ◽  
Force Sensor ◽  
Compensation Method ◽  
Robot Wrist ◽  
New Type ◽  
Genetic Neural Network

The Robot Wrist Sensor Dynamic Mode Building Method Based on Genetic Wavelet Neural Networks

2013 ◽  
Vol 455 ◽  
pp. 389-394
Author(s):  
A Long Yu ◽  
Jin Qiao Dai
Keyword(s):  
Genetic Algorithm ◽  
Neural Networks ◽  
Dynamic Model ◽  
Force Sensor ◽  
Dynamic Mode ◽  
Improved Genetic Algorithm ◽  
Wavelet Neural Networks ◽  
Robot Wrist ◽  
New Type ◽  
Set Up

A kind of new dynamic modeling method is presented based on improved genetic algorithm (IGA) and wavelet neural networks (WNN) and the principle of algorithm is introduced for a new type robot wrist force sensor. The dynamic model of the wrist force sensor is set up according to data of the dynamic calibration, where the structure and parameters of wavelet neural networks of the dynamic model are optimized by genetic algorithm. The results show that the proposed method can overcome the shortcomings of easy convergence to the local minimum points of BP algorithm, and the network complexity, the convergence and the generalization ability are well compromised and the training speed and precision of model are increased.

scholarly journals Dynamic Compensation for Two-Axis Robot Wrist Force Sensors

2013 ◽  
Vol 2013 ◽  
pp. 1-5 ◽  
Author(s):  
Junqing Ma ◽  
Aiguo Song ◽  
Dongcheng Pan
Keyword(s):  
Force Sensor ◽  
Compensation Method ◽  
Step Response ◽  
Order System ◽  
Force Sensors ◽  
Dynamic Compensation ◽  
Pass Filter ◽  
Low Pass Filter ◽  
Low Pass ◽  
Robot Wrist

To improve the dynamic characteristic of two-axis force sensors, a dynamic compensation method is proposed. The two-axis force sensor system is assumed to be a first-order system. The operation frequency of the system is expanded by a digital filter with backward difference network. To filter high-frequency noises, a low-pass filter is added after the dynamic compensation network. To avoid overcompensation, parameters of the proposed dynamic compensation method are defined by trial and error. Step response methods are utilized in dynamic calibration experiments. Compared to experiment data without compensation, the response time of the dynamic compensated data is reduced by 30%~40%. Experiments results demonstrate the effectiveness of our method.

scholarly journals Research on Hysteresis Modeling and Compensation Method of Giant Magnetostrictive Force Sensor

2021 ◽  
Vol 2021 ◽  
pp. 1-19
Author(s):  
Chuanli Wang ◽  
Rui Shi ◽  
Caofeng Yu ◽  
Zhuo Chen ◽  
Yu Wang
Keyword(s):  
Neural Network ◽  
Magnetic Flux ◽  
Flux Density ◽  
Neural Network Model ◽  
Force Sensor ◽  
Bias Current ◽  
Compensation Method ◽  
Magnetic Flux Density ◽  
Input Force ◽  
Variable Bias

Linearity is an important index for evaluating the performance of various sensors. Under the Villari effect, there may be some hysteresis between the input force and the output voltage of a force sensor, meaning that the output will be multivalued and nonlinear. To improve the linearity and eliminate the hysteresis of such sensors, an output compensation method using a variable bias current is proposed based on the bidirectional energy conversion mechanism of giant magnetostrictive material. First, the magnetization relationship between the input force, bias current, and flux density is established. Second, a nonlinear neural network model of the force-magnetization hysteresis and a neural network model for the compensation control of the force sensor are established. These models are trained using the magnetic flux density-force curve and the magnetic flux density-current curve, respectively. Taking the optimal linearity as the objective function, the bias current under different input forces is optimized. Finally, a bias current control system is developed and an experimental test platform is built to verify the proposed method. The results show that the proposed variable bias current hysteresis compensation method enables the linearity under the return of the force sensor to reach 1.6%, which is around 48.3% higher than under previous methods. Thus, the proposed variable bias current method effectively suppresses the hysteresis phenomenon and provides improved linearity for giant magnetostrictive force sensors.

scholarly journals Studying the Potential of Graphcore® IPUs for Applications in Particle Physics

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Samuel Maddrell-Mander ◽  
Lakshan Ram Madhan Mohan ◽  
Alexander Marshall ◽  
Daniel O’Hanlon ◽  
Konstantinos Petridis ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Kalman Filter ◽  
Particle Physics ◽  
Processing Unit ◽  
Network Architectures ◽  
Track Reconstruction ◽  
Event Simulation ◽  
Scattering Correction ◽  
New Type

AbstractThis paper presents the first study of Graphcore’s Intelligence Processing Unit (IPU) in the context of particle physics applications. The IPU is a new type of processor optimised for machine learning. Comparisons are made for neural-network-based event simulation, multiple-scattering correction, and flavour tagging, implemented on IPUs, GPUs and CPUs, using a variety of neural network architectures and hyperparameters. Additionally, a Kálmán filter for track reconstruction is implemented on IPUs and GPUs. The results indicate that IPUs hold considerable promise in addressing the rapidly increasing compute needs in particle physics.

scholarly journals Using Wearable Sensors and a Convolutional Neural Network for Catch Detection in American Football

Sensors ◽  
2020 ◽  
Vol 20 (23) ◽  
pp. 6722
Author(s):  
Bernhard Hollaus ◽  
Sebastian Stabinger ◽  
Andreas Mehrle ◽  
Christian Raschner
Keyword(s):  
Neural Network ◽  
Degrees Of Freedom ◽  
Wearable Sensors ◽  
Professional Sports ◽  
American Football ◽  
Data Logging ◽  
Sensor Platform ◽  
Magnetometer Data ◽  
Audio Data ◽  
New Type

Highly efficient training is a must in professional sports. Presently, this means doing exercises in high number and quality with some sort of data logging. In American football many things are logged, but there is no wearable sensor that logs a catch or a drop. Therefore, the goal of this paper was to develop and verify a sensor that is able to do exactly that. In a first step a sensor platform was used to gather nine degrees of freedom motion and audio data of both hands in 759 attempts to catch a pass. After preprocessing, the gathered data was used to train a neural network to classify all attempts, resulting in a classification accuracy of 93%. Additionally, the significance of each sensor signal was analysed. It turned out that the network relies most on acceleration and magnetometer data, neglecting most of the audio and gyroscope data. Besides the results, the paper introduces a new type of dataset and the possibility of autonomous training in American football to the research community.

Sign in / Sign up

Export Citation Format

Share Document