Multi-Sensor Fault Diagnosis of Underwater Thruster Propeller Based on Deep Learning

With the rapid development of unmanned surfaces and underwater vehicles, fault diagnoses for underwater thrusters are important to prevent sudden damage, which can cause huge losses. The propeller causes the most common type of thruster damage. Thus, it is important to monitor the propeller’s health reliably. This study proposes a fault diagnosis method for underwater thruster propellers. A deep convolutional neural network was proposed to monitor propeller conditions. A Hall element and hydrophone were used to obtain the current signal from the thruster and the sound signal in water, respectively. These raw data were fast Fourier transformed from the time domain to the frequency domain and used as the input to the neural network. The output of the neural network indicated the propeller’s health conditions. This study demonstrated the results of a single signal and the fusion of multiple signals in a neural network. The results showed that the multi-signal input had a higher accuracy than the one-signal input. With multi-signal inputs, training two types of signals with a separated neural network and then merging them at the end yielded the best results (99.88%), as compared to training two types of signals with a single neural network.

Simulative study on the cascaded stages of traveling wave semiconductor optical amplifiers based multiplexing schemes for fiber optic systems improvement

This study has outlined the performance analysis of the cascade traveling-wave optical amplifier (Semiconductor optical amplifier [SOA]) with multiplexing techniques based on fiber communication transceiver systems. The maximum Quality factor is measured against signal power. Signal input power level is enhanced by using the suggested model with previous model. The low pass Bessel filter removes the unwanted ripples from the original signal. The suggested model has clarified better performance efficiency than the previous model.

Machine learning-based broadband GaN HEMT behavioral model applied to class-J power amplifier design

A novel, broadband, nonlinear behavioral model, based on support vector regression (SVR) is presented in this paper. The proposed model, distinct from existing SVR-based models, incorporates frequency information into its formalism, allowing the model to perform accurate prediction across a wide frequency band. The basic theory of the proposed model, along with model implementation and the model extraction procedure for radio frequency transistor devices is provided. The model is verified through comparisons with the simulation of an equivalent circuit model, as well as experimental measurements of a 10 W Gallium Nitride (GaN) transistor. It is seen that the efficiency prediction throughout the Smith chart, for varying fundamental and second harmonic loads, across a wideband frequency range, show excellent fidelity to the measured results. Device dc self-biasing is also modelled to allow prediction of power amplifier (PA) efficiency, which is shown to be highly accurate when compared with corresponding measured data. Finally, a class-J PA is constructed and measured across the frequency with a large-signal input tone. The resulting measured and modelled values of key PA performance figures are shown to be in excellent agreement, indicating the model is suitable for broadband PA design.

The Application and Improvement of Deep Neural Networks in Environmental Sound Recognition

Neural networks have achieved great results in sound recognition, and many different kinds of acoustic features have been tried as the training input for the network. However, there is still doubt about whether a neural network can efficiently extract features from the raw audio signal input. This study improved the raw-signal-input network from other researches using deeper network architectures. The raw signals could be better analyzed in the proposed network. We also presented a discussion of several kinds of network settings, and with the spectrogram-like conversion, our network could reach an accuracy of 73.55% in the open-audio-dataset “Dataset for Environmental Sound Classification 50” (ESC50). This study also proposed a network architecture that could combine different kinds of network feeds with different features. With the help of global pooling, a flexible fusion way was integrated into the network. Our experiment successfully combined two different networks with different audio feature inputs (a raw audio signal and the log-mel spectrum). Using the above settings, the proposed ParallelNet finally reached the accuracy of 81.55% in ESC50, which also reached the recognition level of human beings.

hCINAP is a potential direct HIF-1 target gene and is required for hypoxia-induced EMT and apoptosis in cervical cancer cells

The early metastasis of cervical cancer is a multi-step process requiring the cancer cells to adapt to the signal input from different tissue environments, including hypoxia. Hypoxia-induced epithelial-to-mesenchymal transition (EMT) plays a critical role in the acquisition of the ability to invade surrounding tissue. However, the molecular mechanism underlying EMT in cervical cancer remains to be elucidated. Herein, we showed that HIF‑1α and ARNT are recruited to the hCINAP promoter and initiate hCINAP expression in hypoxia. Ablation of hCINAP decreased the migratory capacity and EMT of cervical cancer cells in hypoxia. Furthermore, hCINAP regulates EMT through Akt/mTOR signaling and inhibits hypoxia-induced p53-dependent apoptosis. Our data collectively showed that hCINAP may have essential roles in the metastasis of cervical cancer and could be a potential target for curing cervical cancer.

Fault Diagnosis of Rotary Machines Using Deep Convolutional Neural Network with Wide Three Axis Vibration 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.

Performance Investigation of AC Servomotor Position Control using Fuzzy Logic and Observer Based Controllers

An AC servomotor which is mostly a two-phase induction motor with two stator field coils placed 90 electrical degrees apart used for controlling position, speed and acceleration in manufacturing industries. In this paper, a two-phase induction motor has been designed with a fuzzy logic and observer based controllers to improve the performance of the system. Comparison of the AC servomotor with the proposed controllers for tracking a step and a square desired position signal input has been done using Matlab/Simulink toolbox and a promising result obtained.