BP Neural Network Prediction Model for Turbulent Noise Intensity in Gas/Water Medium

doi:10.12141/j.issn.1000-565X.240077

Abstract

Abstract:

Addressing the issues of long computation time and low efficiency in numerical solutions for turbulent noise intensity in conventional air/water medium, a neural network prediction model for bluff body/cavity turbulent noise intensity in air/water medium under similar flow conditions was established. This model efficiently predicts aerodynamic noise intensity at the same Reynolds number based on underwater noise intensity, providing technical support for the efficient prediction and control methods of turbulent noise intensity in air/water medium, as well as the research on the interchangeability of noise testing medium. Particle image velocimetry experiments were conducted to measure the flow velocity around open-slot cylinders, validating the effectiveness of the numerical methods. A numerical model for turbulent noise intensity in air/water medium was constructed using the large eddy simulation method, achieving an average velocity calculation error of less than 2.25% and a Strouhal number error of 0.89% between test and simulated values. The numerical model generated 1 338 data points, which were used to construct a training sample dataset. Then, a backpropagation (BP) neural network was built based on key flow parameters to map the relationship between turbulent noise in air/water medium. The Levenberg-Marquardt algorithm was employed to train the predictive model, with the Sigmoid function selected as the activation function. The network comprises 8 input neurons, 1 output neuron, and a single hidden layer. The results demonstrate that the proposed BP neural network prediction model can predict aerodynamic noise intensity at the same Reynolds number as underwater noise intensity, with a maximum prediction error of less than 6.21 dB and an average error of 0.44 dB; that the model exhibits good generalization ability, with an error of 0.27 dB at irregular points in the test set; and that, under comparable hardware conditions, the numerical solution method required approximately 30 hours for computation, while the BP neural network prediction model took only 70 seconds, significantly improving the computational efficiency.

Key words: gas/water medium, turbulent noise, BP neural network, prediction model, open-slot cylinder, particle image velocimetry

CLC Number:

O357.5

ZHU Rui, LIU Yu, LIANG Yuying, SHEN Chuanpeng. BP Neural Network Prediction Model for Turbulent Noise Intensity in Gas/Water Medium[J]. Journal of South China University of Technology(Natural Science Edition), 2024, 52(12): 119-126.

Figures/Tables 16

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Fig.10

Fig.11

Fig.12

Table 1

Table 2

Fig.13

Fig.14

References 28

1	DI MARCO A， BURGHIGNOLI L， CENTRACCHIO F，et al ．Airframe noise measurements in a large hard-walled closed-section wind tunnel［J］．Applied Acoustics，2019，146：96-107．
2	赵成，张涛，侯国祥．基于声扰动方程的矩形柱绕流噪声数值模拟［J］．华中科技大学学报（自然科学版），2021，49（10）：103-108．
	ZHAO Cheng， ZHANG Tao， HOU Guoxiang ．Numerical study on flow noise of flow around rectangular cylinders based on acoustic perturbation equations［J］．Journal of Huazhong University of Science and Technology （Natural Science Edition），2021，49（10）：103-108．
3	MARTIN R， SORIA M， RODRIGUEZ I，et al ．On the flow and passive noise control of an open cavity at Re = 5　000［J］．Flow，Turbulence and Combustion，2022，108（1）：123-148．
4	刘志荣，邹赫，刘锦生，等．开缝圆柱缝隙倾斜角对脱落涡的影响［J］．北京航空航天大学学报，2017，43（1）：128-135．
	LIU Zhirong， ZOU He， LIU Jinsheng，et al ．Effect of angle of slit on shedding vortex of slotted circular cylinder［J］．Journal of Beijing University of Aeronautics and Astronautics，2017，43（1）：128-135．
5	王毅刚，陈垂文，黄晓胜，等．圆柱绕流近壁面处气动噪声源识别研究［J］．声学技术，2019，38（4）：422-427．
	WANG Yigang， CHEN Chuiwen， HUANG Xiaosheng，et al ．Study of identification method for aerodynamic noise sources in flow around cylinder［J］．Technical Acoustics，2019，38（4）：422-427．
6	田斯源，余培汛，白俊强，等．全尺寸起落架的气动及声学特性分析［J］．西北工业大学学报，2022，40（5）：953-961．
	TIAN Siyuan， YU Peixun， BAI Junqiang，et al ．Analysis of aerodynamic and aeroacoustics of full scale landing gear［J］．Journal of Northwestern Polytechnical University，2022，40（5）：953-961．
7	GEYER T F ．Experimental evaluation of cylinder vortex shedding noise reduction using porous material［J］．Experiments in Fluids，2020，61（7）：1-21．
8	任旺．飞机起落架结构件气动噪声分析与降噪方法研究［D］．南京：南京航空航天大学，2016．
9	陈武，周毅．基于K-FWH声比拟方法的串列双圆柱气动噪声研究［J］．北京航空航天大学学报，2021，47（10）：2118-2128．
	CHEN Wu， ZHOU Yi ．Investigation on aeroacoustic of tandem double cylinders by K-FWH acoustic analogy method［J］．Journal of Beijing University of Aeronautics and Astronautics，2021，47（10）：2118-2128．
10	JACOB J， BHATTACHARYA S K ．Aerodynamic noise from long circular and non-circular cylinders using large eddy simulations［J］．International Journal of Aeroacoustics，2022，21（3/4）：142-167．
11	AL-SADAWI L， BIEDERMANN T M， FRITSCHE M ．Passive control of vortex shedding noise of circular cylinders by passive air-jet blowing［J］．Journal of Aerospace Engineering，2021，34（5）：04021060/1-11．
12	LIU H， ZHANG S， CHEN R，et al ．Numerical study on aerodynamic drag and noise of circular cylinders with a porous plate［J］．Aerospace Science and Technology，2022，123：107460/1-15．
13	ZHENG C， ZHOU P， ZHONG S，et al ．An experimental investigation of drag and noise reduction from a circular cylinder using longitudinal grooves［J］．Physics of Fluids，2021，33（11）：115110/1-11．
14	朱睿，李尚，陈子煜，等．二维开缝圆柱环流动力特性［J］．上海交通大学学报，2019，53（10）：1238-1248．
	ZHU Rui， LI Shang， CHEN Ziyu，et al ．Flow field dynamic characteristics of slit cylinders［J］．Journal of Shanghai Jiaotong University，2019，53（10）：1238-1248．
15	ZHU R， ZHUANG Q， LI S，et al ．Overall flow dynamics characteristics of slit-vent cylinders［J］．Aerospace Science and Technology，2020，105：106074/1-11．
16	LYSENKO D A ．Free stream turbulence intensity effects on the flow over a circular cylinder at Re = 3　900：bifurcation， attractors and Lyapunov metric［J］．Ocean Engineering，2023，287：115787/1-14．
17	杨锦文，何意，鲍锋．开缝圆柱近场尾流的大涡模拟和实验测量［J］．空气动力学学报，2014，32（3）：308-314．
	YANG Jinwen， HE Yi， BAO Feng ．Large eddy stimulation and experimental measurement of near wake structures of a slotted circular cylinder［J］．Acta Aerodynamica Sinica，2014，32（3）：308-314．
18	MAYS M D， LARDEAU S， LAIZET S ．Capturing the drag crisis in the flow around a smooth cylinder using a hybrid RANS-LES model on coarse meshes［J］．International Journal of Heat and Fluid Flow，2023，103：109203/1-14．
19	李定远，方斌，李一鸣，等．圆柱绕流特征频率相似性研究［J］．舰船电子工程，2022，42（3）：197-202．
	LI Dingyuan， FANG Bin， LI Yiming，et al ．Study on the similarity of characteristic frequency of flow around a cylinder［J］．Ship Electronic Engineering，2022，42（3）：197-202．
20	眭嘉里．基于数值模拟和BP神经网络的悬垂绝缘子串风偏角预测模型［D］．重庆：重庆大学，2020．
21	姚景瑜，孟海洋，杨京，等．基于BP人工神经网络的轴流风扇气动噪声预测［J］．南京大学学报（自然科学），2020，56（6）：900-908．
	YAO Jingyu， MENG Haiyang， YANG Jing，et al ．Aerodynamic noise prediction of tube-axial fan based on BP artificial neural network［J］．Journal of Nanjing University （Natural Science），2020，56（6）：900-908．
22	王晓玲，杨姝．基于多模型融合的BP神经网络组合预测模型的研究［J］．电脑知识与技术，2023，19（3）：22-25．
	WANG Xiaoling， YANG Shu ．Research on BP neural network combination prediction model based on multi-model fusion［J］．Computer Knowledge and Technology，2023，19（3）：22-25．
23	刘兆荣．基于改进激活函数的卷积神经网络算法及应用研究［D］．上海：上海海洋大学，2019．
24	MENG H， XU X， YANG J，et al ．Fast prediction of aerodynamic noise induced by the flow around a cylinder based on deep neural network［J］．Chinese Physics B，2022，31（6）：064305/1-6．
25	周梦，吕志刚，邸若海，等．基于小样本数据的BP神经网络建模［J］．科学技术与工程，2022，22（7）：2754-2760．
	ZHOU Meng， Zhigang LÜ， DI Rouhai，et al ．BP neural network modeling based on small sample data［J］．Science Technology and Engineering，2022，22（7）：2754-2760．
26	周中，邓卓湘，陈云，等．基于GA-BP神经网络的泡沫轻质土强度预测［J］．华南理工大学学报（自然科学版），2022，50（11）：125-132．
	ZHOU Zhong， DENG Zhuoxiang， CHEN Yun，et al ．Strength prediction of foam light soil based on GA-BP neural network［J］．Journal of South China University of Technology （Natural Science Edition），2022，50（11）：125-132．
27	WANG P， FAN E ．Neural network optimization method and its application in information processing［J］．Mathe-matical Problems in Engineering，2021，1（10）：1-10．
28	赵文清，严海，周震东，等．基于残差BP神经网络的变压器故障诊断［J］．电力自动化设备，2020，40（2）：143-148．
	ZHAO Wenqing， YAN Hai， ZHOU Zhendong，et al ．Fault diagnosis of transformer based on residual BP neural network［J］．Electric Power Automation Equipment，2020，40（2）：143-148．

狭缝比	攻角/（°）	雷诺数	水流速/（mm·s^-1）	空气流速/（mm·s^-1）	监测点坐标/mm	水下总声压级/dB
0.15	0	63 694	1 600	23 259.91	（100，0）	116.176
0.10	30	31 847	800	11 629.95	（200，0）	101.037
0.20	60	63 694	1 600	23 259.91	（0，200）	119.498
0.10	90	47 770	1 200	17 444.93	（100，0）	119.212
0.10	0	63 694	1 600	23 259.91	（0，200）	117.578
0.10	0	47 770	1 200	17 444.93	（300，0）	98.980
0.10	30	31 847	800	11 629.95	（215，0）	100.019
0.20	60	31 847	800	11 629.95	（0，20）	131.598
0.10	60	47 770	1 200	17 444.93	（0，0）	145.261
0.20	90	63 694	1　600	23 259.91	（40，0）	132.211

数值模拟结果/dB	预测结果/dB	绝对误差/dB
107.41	108.98	-1.57
89.06	88.79	0.27
110.57	108.49	2.08
107.56	107.57	-0.01
106.32	105.75	0.57
92.20	92.93	-0.73
88.44	88.17	0.27
119.01	120.15	-1.14
135.27	133.15	2.12
121.71	119.29	2.42

[1]	LAN Fengchong, ZHANG Yue, CHEN Jiqing, et al. Correlation Analysis and Prediction of Pedestrian Casualty Risk in Car-Pedestrian Collision Accident [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(5): 1-10.
[2]	ZHANG Chi, REN Shipeng, WANG Bo, et al. Speed Characteristics and Prediction of Trucks on Long and Steep Downgrade Sections [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(3): 38-49.
[3]	ZHOU Zhong, DENG Zhuoxiang, CHEN Yun, et al. Strength Prediction of Foam Light Soil Based on GA-BP Neural Network [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(11): 125-132.
[4]	ZHANG Yirui SU Jian XU Guan. Research on Coupling Effect Experiment and Decoupling Method of 3-D Force Measuring Platform [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(5): 135-144.
[5]	YANG Chun, LI Penglin, XIONG Shuai, et al. Analysis of Monitoring Data of a Long-Span Steel Roof Based on BIM and BP Neural Network [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(9): 10-19.
[6]	WANG Yihong, ZHANG Jianxiong, LAN Guanqi, et al. Artificial Neural Network Prediction Model for Compressive Strength of Compacted Earth Blocks [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(7): 115-121.
[7]	XUE Cuizhen SHEN Aiqin QIAO Hongxia. Freezing-Thawing Damage Mechanism and Evolution Model of Concrete Mixed with CWCPM [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(3): 136-144.
[8]	. Evaluation of Flow Field Simulation of Turbine in Water-Medium Hydrodynamic Coupling Based on PIV Experiment [J]. Journal of South China University of Technology(Natural Science Edition), 2018, 46(5): 125-134.
[9]	NIU Haiqing WU Juzhuo GUO Shaofeng. Application of Singular Value Decomposition to Pattern Recognition of Partial Discharge in Cable [J]. Journal of South China University of Technology (Natural Science Edition), 2018, 46(1): 26-32.
[10]	BAO Dan-wen LIU Jian-rong GU Jia-yu . Optimization Model of Airport Bus Line Network Reliability and Algorithm Design [J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45(8): 84-91.
[11]	ZENG Xiao-hua LI Guang-han SONG Da-feng LI Sheng ZHU Zhi-cheng. Rollover Warning Algorithm Based on Genetic Algorithm-Optimized BP Neural Network [J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45(2): 30-38.
[12]	NIU Hai-qing WU Ju-zhuo XU Jia ZHENG Wen-jian. Identification of Infrared Images of Cable Terminal Based on Radon Transform and Fourier-Mellin Transform [J]. Journal of South China University of Technology (Natural Science Edition), 2016, 44(8): 47-52,59.
[13]	Zhang Cheng-wei Xiao Bing. Ignition Delay Prediction of Diesel-Natural Gas Blending [J]. Journal of South China University of Technology (Natural Science Edition), 2014, 42(8): 21-26.
[14]	Hu Jun- liang Yu Xiao- lin Zheng Heng- bin Chen Zhou Yan Quan- sheng. Beam Structure Finite Element Model Updating via BP Neural Network Optimized [J]. Journal of South China University of Technology (Natural Science Edition), 2013, 41(8): 67-73.
[15]	Wan Xiao- fang Huang Chun- liu Li You- ming Chai Xin- sheng Hu Hui- chao. Preparation of Functional Polysiloxane via Cationic Miniemulsion Polymerization [J]. Journal of South China University of Technology (Natural Science Edition), 2013, 41(7): 75-80,93.