基于增强特征传递结构神经网络的超磁致伸缩电声换能器输出特性分析

doi:10.19595/j.cnki.1000-6753.tces.241953

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (6915 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract The giant magnetostrictive electroacoustic transducer (GMT) represents a sophisticated underwater device that utilizes the magnetostrictive effect of rare earth giant magnetostrictive materials (GMM) under alternating magnetic fields to achieve efficient electroacoustic energy conversion. This technology demonstrates significant application potential in underwater sonar systems. However, the dynamic performance of GMT is substantially influenced by complex nonlinear electric-magnetic-mechanical-acoustic coupling effects. Traditional frequency-domain methods often fail to accurately represent the input-output relationships, making precise time-domain characteristic analysis crucial for optimal transducer design. Although the time-domain model has the problems of nonlinearity, strong coupling and low computational efficiency, the time-domain characteristics of GMT can be analyzed quickly with the help of deep learning methods. In this context, this paper proposes an enhanced feature transfer structure (EFTS) based on the time-domain model of GMT.
Firstly, based on the Jiles-Atherton hysteresis model of GMM, a time-domain finite element model (FEM) of GMT is established, incorporating the coupling of electromagnetic, mechanical, and acoustic multiple physical fields. The dynamic output characteristics of the transducer are analyzed by the FEM simulation results, and the accuracy of the dynamic model is validated based on existing research. Secondly, to address the issue of long computation time and low efficiency in the GMT FEM model, an EFTS deep learning model is constructed. The neural network is densely connected through a Dense block structure, enabling the reuse of feature information in the channel dimension, thereby accelerating the model’s convergence speed. Thirdly, the GMT EFTS deep learning model is trained to achieve rapid analysis of GMT output characteristics under multi-parameter nonlinear coupling, leveraging small-sample data from the FEM model. Comparative analysis demonstrates that the predicted values of TCR by the EFTS neural network align well with the simulation results, with an RMSE of 0.017, indicating that the proposed method can efficiently and accurately obtain the output characteristics of GMT. Finally, the structural parameters of GMT are optimized based on EFTS neural network and particle swarm optimization algorithm. The optimized structural parameters meet the design requirements and can be used as the final design scheme.
To further validate the feasibility of the proposed design method, a GMT prototype was developed based on the optimized design scheme, and a lake-based experimental platform was constructed. Experimental results demonstrate that at a target water depth of 60 meters, the transducer exhibits a resonant frequency of 450 Hz and achieves a maximum transmit current response (TCR) of 182.79 dB, accompanied by excellent waveform quality. Furthermore, the EFTS neural network prediction results show strong agreement with the experimental data. The feasibility of this method is verified, which provides a new solution for fast and accurate design of GMT.
In summary, the following conclusions can be drawn from the comparative analysis between the model and experimental results: (1) Based on the input and output data of GMT dynamic model, the EFTS neural network model of the transducer is constructed in this paper, which can predict the output characteristics of GMT quickly and accurately and obtain the corresponding design scheme. (2) The GMT EFTS neural network significantly enhances computational efficiency, reducing the single computation time from 14 854 seconds to merely 0.012 9 seconds. (3) The EFTS neural network exhibits high calculation accuracy, with a maximum error of 0.419% and an average error of 0.26% when validated against experimental data, confirming its reliability and precision.

Key words： Giant magnetostrictive electroacoustic transduction multiple physical field coupling enhanced feature transmission structure transmit current response

Received: 30 October 2024

PACS:	TM271
	TB565

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Xu Xiuxian
	Gao Bing
	Wu Zewei
	He Zhixing
	Zhao Nengtong

Cite this article:

Xu Xiuxian,Gao Bing,Wu Zewei等. Analysis of Output Characteristics of Giant Magnetostrictive Electroacoustic Transducer Based on Enhanced Feature Transfer Structure Neural Network[J]. Transactions of China Electrotechnical Society, 2025, 40(23): 7449-7461.

URL:

https://dgjsxb.ces-transaction.com/EN/10.19595/j.cnki.1000-6753.tces.241953 OR https://dgjsxb.ces-transaction.com/EN/Y2025/V40/I23/7449

[1] 宁倩, 李桥, 高兵, 等. 电-磁-机-声多场边界下的超磁致伸缩Ⅳ型弯张换能器设计方法[J]. 电工技术学报, 2023, 38(12): 3112-3121.
Ning Qian, Li Qiao, Gao Bing, et al.Design of giant magnetostrictive class Ⅳ flextensional transducer under electrical-magnetic-mechanical-acoustic multi-field boundaries[J]. Transactions of China Electro-technical Society, 2023, 38(12): 3112-3121.
[2] 刘素贞, 杨圣哲, 张闯, 等. 基于非线性电磁超声表面波混频方法的金属疲劳裂纹检测[J]. 中国电机工程学报, 2021, 41(15): 5371-5381.
Liu Suzhen, Yang Shengzhe, Zhang Chuang, et al.Detection of metal fatigue cracks based on mixing method of nonlinear electromagnetic ultrasonic surface wave[J]. Proceedings of the CSEE, 2021, 41(15): 5371-5381.
[3] 黄文美, 郭万里, 郭萍萍, 等. 基于多目标遗传算法的高频磁致伸缩换能器优化设计[J]. 仪器仪表学报, 2022, 43(1): 111-119.
Huang Wenmei, Guo Wanli, Guo Pingping, et al.Optimization design of high frequency magnetos-trictive transducer based on the multi-objective genetic algorithm[J]. Chinese Journal of Scientific Instrument, 2022, 43(1): 111-119.
[4] 李姝汛, 杨鑫, 陈泽坤, 等. 计及漏磁的堆栈式超磁致伸缩制动器多物理场耦合建模研究[J]. 电工技术学报, 2023, 38(9): 2277-2288.
Li Shuxun, Yang Xin, Chen Zekun, et al.Multi-physics modeling research of stacked giant magnetostrictive actuator considering magnetic flux leakage[J]. Transactions of China Electrotechnical Society, 2023, 38(9): 2277-2288.
[5] Yang Mingzhi, Yang Xin, Wei Yanfei, et al.SPICE modeling of a high-power terfenol-D transducer considering losses and magnetic flux leakage[J]. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2022, 69(2): 812-822.
[6] Zhang Xi, Li Hongguang, Zhao Xie, et al.Numerical analysis and experimental measurement on segmented ring transducer acoustic fields[J]. Applied Acoustics, 2023, 207: 109331.
[7] Guo Rongjing, Li Shiyang, Li Tangan, et al.Analysis and design of low frequency and high power flexten-sional transducer with double-grooves[J]. Applied Acoustics, 2019, 149: 25-31.
[8] Stachowiak D.Finite element analysis of the active element displacement in a giant magnetostrictive transducer[J]. COMPEL: the International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2016, 35(4): 1371-1381.
[9] 陈定方, 舒亮, 卢全国, 等. 超磁致伸缩致动器建模与控制仿真[J]. 机械工程学报, 2007, 43(8): 12-16.
Chen Dingfang, Shu Liang, Lu Quanguo, et al.Modeling and control simulation of giant magnetos-trictive actuator[J]. Chinese Journal of Mechanical Engineering, 2007, 43(8): 12-16.
[10] 夏飞, 许延峰, 胡青. 模拟海豚滴答声的仿生换能器设计[J]. 哈尔滨工程大学学报, 2023, 44(6): 962-968.
Xia Fei, Xu Yanfeng, Hu Qing.Design of a bionic transducer that simulates the ticking sound of dolphins[J]. Journal of Harbin Engineering University, 2023, 44(6): 962-968.
[11] Teng Duo, Li Yatian.Finite element solutions for magnetic field problems in terfenol-D transducers[J]. Sensors, 2020, 20(10): 2808.
[12] 张宇娇, 赵志涛, 徐斌, 等. 基于U-net卷积神经网络的电磁场快速计算方法[J]. 电工技术学报, 2024, 39(9): 2730-2742.
Zhang Yujiao, Zhao Zhitao, Xu Bin, et al.Fast calculation method of electromagnetic field based on U-Net convolutional neural network[J]. Transactions of China Electrotechnical Society, 2024, 39(9): 2730-2742.
[13] 史冬岩, 王立夫, 张博洋, 等. 基于Pyramid-Attention-U-Net深度学习模型的实时拓扑优化设计[J]. 工程力学, 2024, 41(11): 217-224.
Shi Dongyan, Wang Lifu, Zhang Boyang, et al.Real-time topology optimization design upon Pyramid-Attention-U-Net deep learning model[J]. Engineering Mechanics, 2024, 41(11): 217-224.
[14] Guo Yi, Chang Yuan, Lu Bing.A review of temperature prediction methods for oil-immersed transformers[J]. Measurement, 2025, 239: 115383.
[15] 刘云鹏, 高艺倩, 刘刚, 等. 基于U-net神经网络的油浸式变压器绕组流-热耦合快速计算[J]. 中国电机工程学报, 2024, 44(7): 2897-2910.
Liu Yunpeng, Gao Yiqian, Liu Gang, et al.Fast calculation of flow-thermal coupling model of oil-immersed transformer windings based on U-net neural network[J]. Proceedings of the CSEE, 2024, 44(7): 2897-2910.
[16] Guo Pingping, Huang Wenmei, Feng Xiaobo, et al.Hysteresis measurement and generic modeling of magnetostrictive materials under high-frequency excitation and high-intensity bias field[J]. Measure-ment, 2024, 228: 114385.
[17] 黄文美, 薛胤龙, 王莉, 等. 考虑动态损耗的超磁致伸缩换能器的多场耦合模型[J]. 电工技术学报, 2016, 31(7): 173-178.
Huang Wenmei, Xue Yinlong, Wang Li, et al.Multi-field coupling model considering dynamic losses for giant magnetostrictive transducers[J]. Transactions of China Electrotechnical Society, 2016, 31(7): 173-178.
[18] 高兵, 吴泽伟, 赵能桐, 等. 基于AFSA-eCS混合算法的超磁致伸缩换能器输出特性分析[J]. 电工技术学报, 2025, 40(2): 346-357.
Gao Bing, Wu Zewei, Zhao Nengtong, et al.Analysis of output characteristics of giant magnetostrictive transducers based on AFSA-eCS hybrid algorithm[J]. Transactions of China Electrotechnical Society, 2025, 40(2): 346-357.
[19] 滕舵, 杨虎. 水声换能器基础[M]. 2版. 西安: 西北工业大学出版社, 2020.
[20] Huang Gao, Liu Zhuang, Van Der Maaten L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 2017: 2261-2269.
[21] Hou Yuqing, Li Hui, Chen Hong, et al.A novel deep U-Net-LSTM framework for time-sequenced hydrodynamics prediction of the SUBOFF AFF-8[J]. Engineering Applications of Computational Fluid Mechanics, 2022, 16(1): 630-645.
[22] Gong Ruohan, Tang Zuqi.Investigation of convolutional neural network U-Net under small datasets in transformer magneto-thermal coupled analysis[J]. COMPEL-the International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 2020, 39(4): 959-970.
[23] Zheng Jia, Li Shiyang, Wang Bin.Design of low-frequency broadband flextensional transducers based on combined particle swarm optimization and finite element method[J]. Smart Materials and Structures, 2021, 30(10): 105002.