Integrated model of BP neural network and CNN algorithm for automatic wear debris classification

Wang, S.; Wu, Tonghai; Shao, Taihua; Peng, Zhongxiao

doi:10.1016/j.wear.2018.12.087

Cited by 84 publications

(49 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, a three-layer BP neural network (input layer, hidden layer and output layer) was designed to construct a classifier, which can accurately realize any continuous mapping. According to the Kolmogorov theory [ 44 ], the number of neurons in the hidden layer met the condition: D ≥ 2M + 1, where D is the number of neurons in the hidden layer and M is the number of input nerves. The number of neural nodes of the input layer corresponded to the features.…”

Section: Methodsmentioning

confidence: 99%

A Tactile Method for Rice Plant Recognition Based on Machine Learning

Chen

Mao

et al. 2020

Sensors

View full text Add to dashboard Cite

Accurate and real-time recognition of rice plants is the premise underlying the implementation of precise weed control. However, achieving desired results in paddy fields using the traditional visual method is difficult due to the occlusion of rice leaves and the interference of weeds. The objective of this study was to develop a novel rice plant recognition sensor based on a tactile method which acquires tactile information through physical touch. The tactile sensor would be mounted on the paddy field weeder to provide identification information for the actuator. First, a flexible gasbag filled with air was developed, where vibration features produced by tactile and sliding feedback were acquired when this apparatus touched rice plants or weeds, allowing the subtle vibration data with identification features to be reflected through the voltage value of an air-pressured sensor mounted inside the gasbag. Second, voltage data were preprocessed by three algorithms to optimize recognition features, including dimensional feature, dimensionless feature, and fractal dimension. The three types of features were used to train and test a neural network classifier. To maximize classification accuracy, an optimum set of features (b (variance), f (kurtosis), h (waveform factor), l (box dimension), and m (Hurst exponent)) were selected using a genetic algorithm. Finally, the feature-optimized classifier was trained, and the actual performances of the sensor at different contact positions were tested. Experimental results showed that the recognition rates of the end, middle, and root of the sensor were 90.67%, 98%, and 96% respectively. A tactile-based method with intelligence could produce high accuracy for rice plant recognition, as demonstrated in this study.

show abstract

Section: Methodsmentioning

confidence: 99%

A Tactile Method for Rice Plant Recognition Based on Machine Learning

Chen

Mao

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…In DCNN, the activation function has a greater impact on the accuracy of signal recognition, and the commonly used activation functions include Sigmoid, Tanh, Relu, Leaky Relu, Exponential linear units (ELU), and MaxOut, etc. [ 21 , 22 ]. Gradient descent in the network can adjust network back propagation parameters, while the commonly used gradient descent algorithms are stochastic gradient descent (SGD), batch gradient descent (BGD) and MBGD [ 23 ].…”

Section: Methodsmentioning

confidence: 99%

Analysis of the pattern recognition algorithm of broadband satellite modulation signal under deformable convolutional neural networks

Li¹,

Li²

2020

PLoS ONE

View full text Add to dashboard Cite

This research aims to analyze the effects of different parameter estimation on the recognition performance of satellite modulation signals based on deep learning (DL) under low signal to noise ratio (SNR) or channel non-ideal conditions. In this study, first, the common characteristics of broadband satellite modulation signal and the commonly used signal feature extraction algorithm are introduced. Then, the broadband satellite modulation signal pattern recognition model based on deformable convolutional neural networks (DCNN) is built, and the broadband satellite signal simulation is conducted based on Matlab software. Next, the signal characteristics of binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), 8 phase shift keying (PSK), 16 quadratic amplitude modulation (QAM), 64QAM, and 32 absolute phase shift keying (APSK) are extracted by the constellation map, and the ratio changes of T 1 and T 2 with SNR are compared. When SNR is given, it is compared with VGG model, AlexNet model, and ResNe model. The results show that the constellation points of satellite signals with different modulations are evenly distributed. T 1 of PSK modulation signals increases significantly with the increase of SNR. When SNR is greater than 10, PSK modulation signals can be identified. When T 2 is set and SNR is greater than 15dB, 16QAM and 32APSK signals can be distinguished. In the model, the Relu activation function, mini-batch gradient descent (MBGD) algorithm, and Softmax classifier have the best recognition accuracy. PSK modulation signals have the best recognition rate when the SNR is 0dB, and the recognition accuracy of different modulation signals at 20dB is over 98%. When the data length reaches 4000, the recognition accuracy of different modulation signals is higher than 97%. Compared with other algorithms, this algorithm has the highest recognition accuracy (99.83%) and shorter training time (3960s). In conclusion, the broadband satellite modulation signal pattern recognition algorithm of DCNN constructed in this study can effectively identify the patterns of different modulation signals.

show abstract

“…With the development of machine learning, the second generation is denoted by deep learning networks [17][18][19][20][21][22][23]. Peng and Wang [21] proposed a small sample wear particle recognition model based on CNN.…”

Section: Introductionmentioning

confidence: 99%

A Partial Hierarchical Model for Online Low‐Resolution Wear Particle Images Classification

Guo

Tan

Yang

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Wear particle image analysis is an effective method to detect wear condition of mechanical devices. However, the recognition accuracy and recognition efficiency for online wear particle automatic recognition are always mutual restricted because the online wear particle images have almost no texture information and lack clarity. Especially for confusing fatigue wear particles and sliding wear particles, the online recognition is a challenging task. Based on this requirement, a super-resolution reconstruct technique and partial hierarchical convolutional neural network, SR-PHnet, is proposed to classify wear particles in one step. The structure of this network is composed by three modules, one is super-resolution layer module, the second is convolutional neural network classifier module, and the third is support vector machine (SVM) classifier module. The classification result of the second module is partial input to the third module for precision classification of fatigue and sliding particles. In addition, a new feature of radial edge factor (REF) is put forward to target fatigue and sliding wear particles. The test result shows that the new feature has the capability to distinguish fatigue and sliding particles well and time saving. The comparison experiments of the convolution neural network (CNN) method, support vector machine method (SVM) with and without REF feature, and integrated model of back-propagation (BP) and CNN are produced. The comparison results show that the online recognition speed and online recognition rate of the proposed SR-PHnet model in this paper are both improved markedly, especially for fatigue and sliding wear particles.

show abstract

Integrated model of BP neural network and CNN algorithm for automatic wear debris classification

Cited by 84 publications

References 28 publications

A Tactile Method for Rice Plant Recognition Based on Machine Learning

A Tactile Method for Rice Plant Recognition Based on Machine Learning

Analysis of the pattern recognition algorithm of broadband satellite modulation signal under deformable convolutional neural networks

A Partial Hierarchical Model for Online Low‐Resolution Wear Particle Images Classification

Contact Info

Product

Resources

About