[1]YANG Zhengli,WU Fuyun,CHEN Haixia.Fault identification of multi-feature boiler tube acoustic signal based on deep residual shrinkage network[J].CAAI Transactions on Intelligent Systems,2023,18(5):1108-1116.[doi:10.11992/tis.202207012]
Copy

Fault identification of multi-feature boiler tube acoustic signal based on deep residual shrinkage network

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 18 Number of periods: 2023 5 Page number: 1108-1116 Column: 学术论文—机器学习 Public date: 2023-09-05
Title:
Fault identification of multi-feature boiler tube acoustic signal based on deep residual shrinkage network
Author(s):
YANG Zhengli;  WU Fuyun;  CHEN Haixia
School of Mechanical and Electrical Engineering, Sanjiang University, Nanjing 210012, China
Keywords:
deep learning; fault identification; deep residual shrinkage network; bidirectional short and long memory network; attention mechanism; convolutional neural network; boiler tube; acoustic signal
CLC:
TP391；TN912.3；TM621.2
DOI:
10.11992/tis.202207012
Abstract:
To improve the learning effect and recognition accuracy in fault identification of boiler tube acoustic signals, different information fusion mechanisms were used in this study. Specifically, feature vector parallelism and splicing techniques are used to form the feature layer, while the decision layer is formed using average and maximum score approaches. A fault identification method of multifeature boiler tube acoustic signal based on a deep residual shrinkage network is proposed. First, the first-order and second-order differential characteristics of the acoustic signal spectrum were calculated separately, considering the variations of acoustic wave sensors on the boiler tube. This process constructs a three-channel feature set, which serves as the input feature vector of the two-dimensional network. Subsequently, an attentional mechanism is introduced to construct a baseline model using a combination of a convolutional neural network and a bidirectional short and long memory network. Additionally, a deep residual shrinkage network is used to optimize the allocation of channel weights within the two-dimensional network to improve the fault identification accuracy of the model. Extensive experimental results show that: it is a more effective strategy to construct the information fusion mechanism of the feature layer by using feature vector parallel fusion; compared with the baseline model, the unweighted average recall rate has increased by 4.32%, highlighting significant improvements in the recognition accuracy of the model presented in this paper.
References:
[1] 何俊松. 炉管泄漏自动报警装置的技术改造[J]. 广西电力, 2018, 41(1): 63-66
HE Junsong. Technical modification of automatic warning system of boiler pipe leakage[J]. Guangxi electric power, 2018, 41(1): 63-66
[2] OH H, JUNG J H, JEON B C, et al. Scalable and unsupervised feature engineering using vibration-imaging and deep learning for rotor system diagnosis[J]. IEEE transactions on industrial electronics, 2018, 65(4): 3539-3549.
[3] BOU-GHAZALE S E, HANSEN J H L. A comparative study of traditional and newly proposed features for recognition of speech under stress[J]. IEEE transactions on speech and audio processing, 2000, 8(4): 429-442.
[4] LAUKKA P, NEIBERG D, FORSELL M, et al. Expression of affect in spontaneous speech: acoustic correlates and automatic detection of irritation and resignation[J]. Computer speech & language, 2011, 25(1): 84-104.
[5] HSIAO P W, CHEN C P. Effective attention mechanism in dynamic models for speech emotion recognition[C]//2018 IEEE International Conference on Acoustics, Speech and Signal Processing. Calgary: IEEE, 2018: 2526?2530.
[6] LIU Ruonan, YANG Boyuan, ZIO E, et al. Artificial intelligence for fault diagnosis of rotating machinery: a review[J]. Mechanical systems and signal processing, 2018, 108: 33-47.
[7] HAN Zhiyan, WANG Jian. Speech emotion recognition based on Gaussian kernel nonlinear proximal support vector machine[C]//2017 Chinese Automation Congress. Jinan: IEEE, 2018: 2513?2516.
[8] LI Yifan, LIANG Xihui, LIN Jianhui, et al. Train axle bearing fault detection using a feature selection scheme based multi-scale morphological filter[J]. Mechanical systems and signal processing, 2018, 101: 435-448.
[9] 胡德生, 张雪英, 张静, 等. 基于主辅网络特征融合的语音情感识别[J]. 太原理工大学学报, 2021, 52(5): 769-774
HU Desheng, ZHANG Xueying, ZHANG Jing, et al. Feature fusion based on main-auxiliary network for speech emotion recognition[J]. Journal of Taiyuan University of Technology, 2021, 52(5): 769-774
[10] KIM J, SAUROUS R A. Emotion recognition from human speech using temporal information and deep learning[C]//Proc Interspeech 2018. Hyderabad: ISCA, 2018: 937?940.
[11] 胡康, 何思宇, 左敏, 等. 基于CNN-BLSTM的化妆品违法违规行为分类模型[J]. 智能系统学报, 2021, 16(6): 1151-1157
HU Kang, HE Siyu, ZUO Min, et al. Classification model for judging illegal and irregular behavior for cosmetics based on CNN-BLSTM[J]. CAAI transactions on intelligent systems, 2021, 16(6): 1151-1157
[12] 刘威, 王薪予, 刘光伟, 等. 融合关系特征的半监督图像分类方法研究[J]. 智能系统学报, 2022, 17(5): 886-899
LIU Wei, WANG Xinyu, LIU Guangwei, et al. Semi-supervised image classification method fused with relational features[J]. CAAI transactions on intelligent systems, 2022, 17(5): 886-899
[13] 苏丽, 孙雨鑫, 苑守正. 基于深度学习的实例分割研究综述[J]. 智能系统学报, 2022, 17(1): 16-31
SU Li, SUN Yuxin, YUAN Shouzheng. A survey of instance segmentation research based on deep learning[J]. CAAI transactions on intelligent systems, 2022, 17(1): 16-31
[14] 胡海华, 韩国军, 张孝谊. 基于卷积神经网络的闪存信道检测技术研究[J]. 智能系统学报, 2021, 16(6): 1090-1097
HU Haihua, HAN Guojun, ZHANG Xiaoyi. Research on flash memory channel detection technology based on convolutional neural network[J]. CAAI transactions on intelligent systems, 2021, 16(6): 1090-1097
[15] 潘国壮. 基于实时陆空通话情感识别的管制员疲劳状态快速监测研究[D]. 南京: 南京航空航天大学, 2020.
PAN Guozhuang. Research on rapid monitoring of air traffic controller’s fatigue state based on real-time emotion recognition of land-air communication[D]. Nanjing: Nanjing University of Aeronautics and Astronautics, 2020.
[16] FARHOUDI Z, SETAYESHI S. Fusion of deep learning features with mixture of brain emotional learning for audio-visual emotion recognition[J]. Speech communication, 2021, 127: 92-103.
[17] 李瑞航, 吴红兰, 孙有朝, 等. 基于深度残差收缩网络多特征融合语音情感识别[J]. 数据采集与处理, 2022, 37(3): 542-554
LI Ruihang, WU Honglan, SUN Youchao, et al. Speech emotion recognition base on multi-feature fusion of deep residual shrinkage network[J]. Journal of data acquisition and processing, 2022, 37(3): 542-554
[18] DANGOL R, ALSADOON A, PRASAD P W C, et al. Speech emotion recognition using convolutional neural network and long-short term memory[J]. Multimedia tools and applications, 2020, 79(43/44): 32917-32934.
[19] 胡婷婷, 冯亚琴, 沈凌洁, 等. 基于注意力机制的LSTM语音情感主要特征选择[J]. 声学技术, 2019, 38(4): 414-421
HU Tingting, FENG Yaqin, SHEN Lingjie, et al. The salient feature selection by attention mechanism based LSTM in speech emotion recognition[J]. Technical acoustics, 2019, 38(4): 414-421
[20] 姜特, 陈志刚, 万永菁. 基于注意力机制的多任务3D CNN-BLSTM情感语音识别[J]. 华东理工大学学报(自然科学版), 2022, 48(4): 534-542
JIANG Te, CHEN Zhigang, WAN Yongjing. Multi-task learning 3D CNN-BLSTM with attention mechanism for speech emotion recognition[J]. Journal of East China University of Science and Technology(natural science edition), 2022, 48(4): 534-542
[21] GAO Zehai, MA Cunbao, SONG Dong, et al. Deep quantum inspired neural network with application to aircraft fuel system fault diagnosis[J]. Neurocomputing, 2017, 238: 13-23.
[22] SOHAIB M, KIM C H, KIM J M. A hybrid feature model and deep-learning-based bearing fault diagnosis[J]. Sensors (Basel, Switzerland), 2017, 17(12): 2876.
[23] GUPTA A, ANJUM, GUPTA S, et al. InstaCovNet-19: A deep learning classification model for the detection of COVID-19 patients using Chest X-ray[J]. Applied soft computing, 2020, 99: 1-13.
[24] 陈捷, 陆云. 2016年度上海并网发电厂发电锅炉“四管”泄漏统计及案例分析[J]. 电力与能源, 2017, 38(2): 170-175
CHEN Jie, LU Yun. Statistics and case analysis of Shanghai grid plant power boiler four-tube leakages in 2016[J]. Power & energy, 2017, 38(2): 170-175
[25] WANG Tao, PEI Yu, XIAO Huiheng, et al. Detection of small gas leaks based on neural networks and D-S evidential theory using ultrasonics[J]. Insight-non-destructive testing and condition monitoring, 2014, 56(4): 189-194.
[26] 宁方立, 韩鹏程, 段爽, 等. 基于改进CNN的阀门泄漏超声信号识别方法[J]. 北京邮电大学学报, 2020, 43(3): 38-44
NING Fangli, HAN Pengcheng, DUAN Shuang, et al. Identification method of valve leakage ultrasonic signal based on improved CNN[J]. Journal of Beijing University of Posts and Telecommunications, 2020, 43(3): 38-44
[27] ZHAO Minghang, ZHONG Shisheng, FU Xuyun, et al. Deep residual shrinkage networks for fault diagnosis[J]. IEEE transactions on industrial informatics, 2020, 16(7): 4681-4690.
[28] 卢锦玲, 郭鲁豫. 基于改进深度残差收缩网络的电力系统暂态稳定评估[J]. 电工技术学报, 2021, 36(11): 2233-2244
LU Jinling, GUO Luyu. Power system transient stability assessment based on improved deep residual shrinkage network[J]. Transactions of China electrotechnical society, 2021, 36(11): 2233-2244
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems