Development of neural networks chip generating driving waveform for electrostatic motor

2021 ◽  
Author(s):  
Takuro Sasaki ◽  
Mika Kurosawa ◽  
Yu Usami ◽  
Shinya Kato ◽  
Arisa Sakaki ◽  
...  
Keyword(s):  
Neural Networks ◽  
Integrated Circuit ◽  
Synaptic Weight ◽  
Low Frequency ◽  
Waveform Generator ◽  
Two Phase ◽  
Body Model ◽  
The Neural Networks ◽  
Driving Waveform ◽  
Driving Circuit

AbstractThe authors are studying hardware neural networks (HNN) to control the locomotion of the microrobot. The neural networks chip is the integrated circuit chip of the HNN. We proposed the electrostatic motor that is the new actuator of the microrobot in our previous research. The electrostatic motor used the waveform generator to generate the driving waveform. In this paper, the authors will propose the driving circuit using neural networks chip. The cell body model is the basic component of the neural networks chip that outputs 3 MHz frequency of electrical oscillated pulse waveform. Therefore, large capacitors need to connect outside of the neural networks chip to generate the low-frequency driving waveform. The proposal neural networks chip generates a long delay without using large capacitors. In addition, the neural networks chip generated a two-phase anti-phase synchronized waveform by incorporating a mechanism for adjusting synaptic weight. As a result, the proposal neural networks chip can generate the electrostatic motor’s driving waveform with variable frequency. The frequency of the driving waveform could vary from 40 to 126 Hz.

MEMS Microrobot with Pulse-Type Hardware Neural Networks Integrated Circuit

2015 ◽  
pp. 18-35 ◽  
Author(s):  
Ken Saito ◽  
Minami Takato ◽  
Yoshifumi Sekine ◽  
Fumio Uchikoba
Keyword(s):  
Neural Networks ◽  
Integrated Circuit ◽  
Pulse Waveform ◽  
Biologically Inspired ◽  
Micro Electro Mechanical Systems ◽  
Controlling System ◽  
Pulse Type ◽  
The Neural Networks ◽  
Mechanical Components ◽  
Electrical Components

Hexapod locomotive Micro-Electro Mechanical Systems (MEMS) microrobot with Pulse-type Hardware Neural Networks (P-HNN) locomotion controlling system is presented in this chapter. MEMS microrobot is less than 5 mm width, length, and height in size. MEMS microrobot is made from a silicon wafer fabricated by micro fabrication technology to realize the small size mechanical components. The mechanical components of MEMS microrobot consists of body frames, legs, link mechanisms, and small size actuators. In addition, MEMS microrobot has a biologically inspired locomotion controlling system, which is the small size electrical components realized by P-HNN. P-HNN generates the driving pulses for actuators of the MEMS microrobot using pulse waveform such as biological neural networks. The MEMS microrobot emulates the locomotion method and the neural networks of an insect with small size actuator, link mechanisms, and P-HNN. As a result, MEMS microrobot performs hexapod locomotion using the driving pulses generated by P-HNN.

MEMS Microrobot with Pulse-Type Hardware Neural Networks Integrated Circuit

2016 ◽  
pp. 630-647
Author(s):  
Ken Saito ◽  
Minami Takato ◽  
Yoshifumi Sekine ◽  
Fumio Uchikoba
Keyword(s):  
Neural Networks ◽  
Integrated Circuit ◽  
Pulse Waveform ◽  
Biologically Inspired ◽  
Micro Electro Mechanical Systems ◽  
Controlling System ◽  
Pulse Type ◽  
The Neural Networks ◽  
Mechanical Components ◽  
Electrical Components

Hexapod locomotive Micro-Electro Mechanical Systems (MEMS) microrobot with Pulse-type Hardware Neural Networks (P-HNN) locomotion controlling system is presented in this chapter. MEMS microrobot is less than 5 mm width, length, and height in size. MEMS microrobot is made from a silicon wafer fabricated by micro fabrication technology to realize the small size mechanical components. The mechanical components of MEMS microrobot consists of body frames, legs, link mechanisms, and small size actuators. In addition, MEMS microrobot has a biologically inspired locomotion controlling system, which is the small size electrical components realized by P-HNN. P-HNN generates the driving pulses for actuators of the MEMS microrobot using pulse waveform such as biological neural networks. The MEMS microrobot emulates the locomotion method and the neural networks of an insect with small size actuator, link mechanisms, and P-HNN. As a result, MEMS microrobot performs hexapod locomotion using the driving pulses generated by P-HNN.

scholarly journals Non-programmed gait generation of quadruped robot using pulse-type hardware neuron models

2020 ◽  
Author(s):  
Yuki Takei ◽  
Katsuyuki Morishita ◽  
Riku Tazawa ◽  
Koichi Katsuya ◽  
Ken Saito
Keyword(s):  
Neural Networks ◽  
Weight Control ◽  
Synaptic Weight ◽  
Quadruped Robot ◽  
Control Voltage ◽  
Neuron Models ◽  
Gait Generation ◽  
Body Model ◽  
Pulse Type ◽  
Synaptic Model

Abstract In this paper, the authors will propose the active gait generation of a quadruped robot. The theory that quadruped animals unconsciously generate gaits by some system based on neural networks in the spinal cord is widely accepted. However, how biological neurons or neural networks can generate gaits is not clear. To clarify the gait generation method, one of the solutions is using the neuron model similar to the biological neuron. We developed the quadruped robot system using self-inhibited pulse-type hardware neuron models (P-HNMs), which can output the electrical activity similar to those of biological neurons. The P-HNMs consist of the cell body model and the inhibitory synaptic model. The cell body model periodically outputs pulsed voltages; the inhibitory synaptic model inhibits the pulsed voltages. The pulse period can change by varying the synaptic weight control voltage applied to the P-HNMs. We varied the synaptic weight control voltage according to the pressure on the robot’s toes. Also, we changed the angle of the robot’s joints by a constant angle each time the P-HNMs output a pulse. As a result of the walking experiment, we confirmed that the robot generates walk gait and trot gait according to the moving speed. Also, we clarified the process by which the robot actively generates gaits from the upright state. These results show that animals may not use many biological neurons to generate gaits. Furthermore, the results suggest the possibility of realizing simple and bio-inspired robot control.

A Novel Two-phase Soft Starter Used for Three-phase Asynchronous Motors

2020 ◽  
Vol 13 (8) ◽  
pp. 1175-1182
Author(s):  
Jingwen Chen ◽  
Hongshe Dang
Keyword(s):  
Pulse Generation ◽  
Power Module ◽  
Two Phase ◽  
Power Semiconductor ◽  
Starting Current ◽  
Semiconductor Switches ◽  
Soft Starter ◽  
Three Phase ◽  
And Control ◽  
Driving Circuit

Background: Traditional thyristor-based three-phase soft starters of induction motor often suffer from high starting current and heavy harmonics. Moreover, both the trigger pulse generation and driving circuit design are usually complicated. Methods: To address these issues, we propose a novel soft starter structure using fully controlled IGBTs in this paper. Compared to approaches of traditional design, this structure only uses twophase as the input, and each phase is controlled by a power module that is composed of one IGBT and four diodes. Results: Consequently, both driving circuit and control design are greatly simplified due to the requirement of fewer controlled power semiconductor switches, which leads to the reduction of the total cost. Conclusion: Both Matlab/Simulink simulation results and experimental results on a prototype demonstrate that the proposed soft starter can achieve better performances than traditional thyristorbased soft starters for Starting Current (RMS) and harmonics.

scholarly journals Tax Fraud Detection through Neural Networks: An Application Using a Sample of Personal Income Taxpayers

2019 ◽  
Vol 11 (4) ◽  
pp. 86 ◽  
Author(s):  
César Pérez López ◽  
María Delgado Rodríguez ◽  
Sonia de Lucas Santos
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Income Tax ◽  
Fraud Detection ◽  
Personal Income ◽  
Personal Income Tax ◽  
Tax Returns ◽  
The Neural Networks ◽  
Tax Fraud ◽  
Efficiency Rate

The goal of the present research is to contribute to the detection of tax fraud concerning personal income tax returns (IRPF, in Spanish) filed in Spain, through the use of Machine Learning advanced predictive tools, by applying Multilayer Perceptron neural network (MLP) models. The possibilities springing from these techniques have been applied to a broad range of personal income return data supplied by the Institute of Fiscal Studies (IEF). The use of the neural networks enabled taxpayer segmentation as well as calculation of the probability concerning an individual taxpayer’s propensity to attempt to evade taxes. The results showed that the selected model has an efficiency rate of 84.3%, implying an improvement in relation to other models utilized in tax fraud detection. The proposal can be generalized to quantify an individual’s propensity to commit fraud with regards to other kinds of taxes. These models will support tax offices to help them arrive at the best decisions regarding action plans to combat tax fraud.

Neural networks trained with high-dimensional functions approximation data in high-dimensional space

2021 ◽  
pp. 1-12
Author(s):  
Jian Zheng ◽  
Jianfeng Wang ◽  
Yanping Chen ◽  
Shuping Chen ◽  
Jingjin Chen ◽  
...  
Keyword(s):  
Neural Networks ◽  
Dimensional Space ◽  
Data Distribution ◽  
High Dimensional ◽  
Sufficient Information ◽  
Sufficient Data ◽  
High Dimensional Space ◽  
Positive Effects ◽  
The Neural Networks ◽  
Using Data

Neural networks can approximate data because of owning many compact non-linear layers. In high-dimensional space, due to the curse of dimensionality, data distribution becomes sparse, causing that it is difficulty to provide sufficient information. Hence, the task becomes even harder if neural networks approximate data in high-dimensional space. To address this issue, according to the Lipschitz condition, the two deviations, i.e., the deviation of the neural networks trained using high-dimensional functions, and the deviation of high-dimensional functions approximation data, are derived. This purpose of doing this is to improve the ability of approximation high-dimensional space using neural networks. Experimental results show that the neural networks trained using high-dimensional functions outperforms that of using data in the capability of approximation data in high-dimensional space. We find that the neural networks trained using high-dimensional functions more suitable for high-dimensional space than that of using data, so that there is no need to retain sufficient data for neural networks training. Our findings suggests that in high-dimensional space, by tuning hidden layers of neural networks, this is hard to have substantial positive effects on improving precision of approximation data.

Ion-gating synaptic transistors with long-term synaptic weight modulation

2021 ◽  
Vol 9 (16) ◽  
pp. 5396-5402
Author(s):  
Youngjun Park ◽  
Min-Kyu Kim ◽  
Jang-Sik Lee
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Synaptic Weight ◽  
Recognition Accuracy ◽  
Artificial Neural ◽  
High Recognition Accuracy

This paper presents synaptic transistors that show long-term synaptic weight modulation via injection of ions. Linear and symmetric weight update is achieved, which enables high recognition accuracy in artificial neural networks.

Classification and Recognition of Plant Leaf Based on Neural Networks

2011 ◽  
Vol 464 ◽  
pp. 38-42 ◽  
Author(s):  
Ping Ye ◽  
Gui Rong Weng
Keyword(s):  
Neural Networks ◽  
Fractal Dimension ◽  
Recognition Rate ◽  
Image Binarization ◽  
Characteristic Parameters ◽  
Moment Invariant ◽  
Plant Leaf ◽  
The Neural Networks ◽  
Novel Method ◽  
The Moment

This paper proposed a novel method for leaf classification and recognition. In the method, the moment invariant and fractal dimension were regarded as the characteristic parameters of the plant leaf. In order to extract the representative characteristic parameters, pretreatment of the leaf images, including RGB-gray converting, image binarization and leafstalk removing. The extracted leaf characteristic parameters were further utilized as training sets to train the neural networks. The proposed method was proved effectively to reach a recognition rate about 92% for most of the testing leaf samples

scholarly journals Localization of Scattering Objects Using Neural Networks

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 11
Author(s):  
Domonkos Haffner ◽  
Ferenc Izsák
Keyword(s):  
Neural Networks ◽  
Plane Waves ◽  
Measurement Data ◽  
Scattered Wave ◽  
Training Data ◽  
Data Set ◽  
Main Compound ◽  
Incident Plane ◽  
The Neural Networks ◽  
Simulation Package

The localization of multiple scattering objects is performed while using scattered waves. An up-to-date approach: neural networks are used to estimate the corresponding locations. In the scattering phenomenon under investigation, we assume known incident plane waves, fully reflecting balls with known diameters and measurement data of the scattered wave on one fixed segment. The training data are constructed while using the simulation package μ-diff in Matlab. The structure of the neural networks, which are widely used for similar purposes, is further developed. A complex locally connected layer is the main compound of the proposed setup. With this and an appropriate preprocessing of the training data set, the number of parameters can be kept at a relatively low level. As a result, using a relatively large training data set, the unknown locations of the objects can be estimated effectively.

Sign in / Sign up

Export Citation Format

Share Document