scholarly journals Diagnosis Kerosakan Litar Menggunakan Pspice dan Rangkaian Neural Tiruan

2012 ◽  
Author(s):  
Jasronita Jasni ◽  
Samsul Bahari Mohd Noor ◽  
Ribhan Zafira Abd Rahman
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Diagnosis ◽  
Power Supply ◽  
Pulse Width ◽  
Analog Circuit ◽  
Switch Mode Power Supply ◽  
Pulse Width Modulator ◽  
Switch Mode ◽  
The Individual

Kerosakan komponen di dalam satu litar sangat sukar dikesan dan mengambil masa yang lama untuk dikenalpasti. Kertas ini membentangkan kaedah mendiagnosis kerosakan litar menggunakan Rangkaian Neural Tiruan (RNT). Litar Pengayun dan Pulse Width Modulator yang merupakan sebahagian dari Switch Mode Power Supply telah digunakan sebagai litar kajian. Litar ini disimulasi menggunakan Pspice dan data voltan pada nod direkodkan dan digunakan dalam sistem rangkaian neural tiruan. Setelah dilatih, sistem ini berupaya mengenalpasti komponen yang rosak dengan mudah. Kata kunci: Diagnosis kerosakan, litar analog, rangkaian neural Faulty components in a circuit is difficult and time consuming to be identified. This paper presents a method of circiut fault diagnosis using artificial neural networks (ANN). Oscillator circuit with Pulse Width Modulator which is part of a Switch Mode Power Supply is used in this study. The system is trained and able to identify the individual faulty components with ease. Key words: Fault diagnosis, analog circuit, neural network

scholarly journals Analysis and design of an asynchronous pulse‐width modulation technique for switch mode power supply

2020 ◽  
Vol 13 (8) ◽  
pp. 1639-1648
Author(s):  
Reza Inanlou ◽  
Omid Shoaei ◽  
Mohsen Tamaddon ◽  
Michael Rescati ◽  
Andrea Baschirotto
Keyword(s):  
Power Supply ◽  
Pulse Width ◽  
Pulse Width Modulation ◽  
Switch Mode Power Supply ◽  
Analysis And Design ◽  
Modulation Technique ◽  
Switch Mode

Information-Applied Technology in Fault Diagnosis Model of RBF Neural Network Based on PSO Algorithm for Analog Circuit

2014 ◽  
Vol 540 ◽  
pp. 452-455
Author(s):  
Xiao Hua Zhang ◽  
Hua Ping Li
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Analog Circuit ◽  
Rbf Neural Network ◽  
Pso Algorithm ◽  
Local Optimum ◽  
Connection Weight ◽  
Diagnosis Method ◽  
The Individual ◽  
Network Diagnosis

To improve the ability of fault diagnosis for analog circuit, a RBF neural network diagnosis method trained by an improved Particle Swarm Optimization (PSO) algorithm is proposed. In order to overcome the shortcoming of the traditional BP algorithm of RBF neural network, PSO algorithm is introduced to optimize the center, width and connection weight of RBF neural network. And the mutation operator is inserted to ensure the individual in swarm out of the local optimum. The simulation shows that the proposed modeling algorithm has the better convergence and diagnosis characteristics.

WNN Model Based on Particle Swarm Optimization for Fault Diagnosis in Analog Circuit

2013 ◽  
Vol 427-429 ◽  
pp. 1048-1051
Author(s):  
Xu Sheng Gan ◽  
Hao Lin Cui ◽  
Ya Rong Wu
Keyword(s):  
Neural Network ◽  
Particle Swarm Optimization ◽  
Fault Diagnosis ◽  
Convergence Rate ◽  
Analog Circuit ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Wavelet Neural Network ◽  
Swarm Optimization ◽  
Fast Convergence Rate

In order to diagnose the fault in analog circuit correctly, a Wavelet Neural Network (WNN) method is proposed that uses the Particle Swarm Optimization (PSO) algorithm to optimize the network parameters. For the improvement of convergence rate in WNN based on PSO algorithm, a compressing method in research space is introduced into the traditional PSO algorithm to improve the convergence in WNN training. The simulation shows that the proposed method has a good diagnosis with fast convergence rate for the fault in analog circuit.

scholarly journals Fault Diagnosis of Rotary Machines Using Deep Convolutional Neural Network with Wide Three Axis Vibration Signal Input

Sensors ◽  
2020 ◽  
Vol 20 (14) ◽  
pp. 4017 ◽  
Author(s):  
Davor Kolar ◽  
Dragutin Lisjak ◽  
Michał Pająk ◽  
Danijel Pavković
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Fault Diagnosis ◽  
Convolutional Neural Network ◽  
Input Matrix ◽  
Accelerometer Signal ◽  
Rotary Machinery ◽  
Signal Input

Fault diagnosis is considered as an essential task in rotary machinery as possibility of an early detection and diagnosis of the faulty condition can save both time and money. This work presents developed and novel technique for deep-learning-based data-driven fault diagnosis for rotary machinery. The proposed technique input raw three axes accelerometer signal as high definition 1D image into deep learning layers which automatically extract signal features, enabling high classification accuracy. Unlike the researches carried out by other researchers, accelerometer data matrix with dimensions 6400 × 1 × 3 is used as input for convolutional neural network training. Since convolutional neural networks can recognize patterns across input matrix, it is expected that wide input matrix containing vibration data should yield good classification performance. Using convolutional neural networks (CNN) trained model, classification in one of the four classes can be performed. Additionally, number of kernels of CNN is optimized using grid search, as preliminary studies show that alternating number of kernels impacts classification results. This study accomplished the effective classification of different rotary machinery states using convolutional artificial neural network for classification of raw three axis accelerometer signal input.

Sign in / Sign up

Export Citation Format

Share Document