水声换能器是水声传感系统的核心部件,其性能直接影响系统的灵敏度、精度和可靠性.然而,传统的水声换能器参数测试方法存在数据处理量过大和算法精度较低的问题.为此,本文提出了一种基于I-GWO-LSTM(improved-grey wolf optimization algorithm-long short-term memory)的水声换能器参数预测模型.该模型利用改进灰狼优化算法优化长短期记忆网络模型的参数,只需要测量少量数据点就可以实现对水声换能器等效电路元件参数的高精度预测.通过MATLAB进行仿真实验,验证了该模型在水声换能器参数预测方面具有较高的准确性和稳定性.
Abstract
The hydrophone transducer is the core component of the underwater acoustic sensing system,and its performance directly affects the sensitivity,accuracy,and reliability of the system.However,traditional methods for testing hydrophone transducer parameters suffer from problems such as excessive data processing and low algorithmic accuracy.To address this issue,this paper proposes a hydrophone transducer parameter prediction model based on I-GWO-LSTM(improved-grey wolf optimization algorithm-long short-term memory).The model uses an improved grey wolf optimization algorithm to optimize the parameters of the long short-term memory network model,and with only a small amount of data points,achieves high-precision prediction of the equivalent circuit element parameters of the hydrophone transducer.Simulation experiments conducted using MATLAB confirm that the proposed model has high accuracy and stability in predicting hydrophone transducer parameters.
关键词
改进灰狼算法/长短期记忆网络/水声换能器/参数预测
Key words
improved grey wolf algorithm/long short-term memory network(LSTM)/hydrophone transducer/parameter prediction
维普
万方数据