淤泥质海底航道边坡失稳程度评估与预测

Evaluation and prediction of instability degree of muddy submarine channel

淤泥质海底航道边坡稳定性对于航道安全运行至关重要。由于航道边坡失稳滑塌具有不确定性,无法对其失稳程度进行预测评估,严重影响过往船只安全和航道管理维护。基于工程试验模拟的方式获取航道边坡失稳滑塌全周期声纹图像,通过分析声纹图像能量变化将其失稳过程划分为:非常稳定、稳定、不稳定、极不稳定、滑塌5个阶段。基于Gabor变换提取各阶段声纹图像特征,利用离散余弦变换进行特征降维,将降维后的声纹图像特征输入Fisher函数中构建失稳程度评估预测模型。结果表明:将待评估声纹图像样本特征输入到预测模型中,识别正确率达到90%。因此,基于Gabor特征构建Fisher模型进行淤泥质海底航道边坡失稳程度评估预测是可行的,对研究航道边坡稳定性具有重要意义。

The slope stability of muddy submarine channel is very important for the safe operation of the channel.Due to the uncertainty of channel slope instability and collapse,it is impossible to predict and evaluate the degree of instability,which seriously affects the safety of passing ships and management and maintenance of the channel.Based on the engineering experiment simulation,this paper obtains the full cycle voiceprint image of channel slope instability and collapse.By analyzing the energy change of voiceprint image,the instability process is divided into five stages:very stable,stable,unstable,extremely unstable and collapse.The voiceprint image features at each stage are extracted based on the Gabor transform,and the discrete cosine transform is used to reduce the dimensionality of the features.The voiceprint image features after the dimensionality reduction are input into Fisher function to build the instability degree evaluation and prediction model.The results show that the recognition accuracy reaches 90%when the features of voiceprint image samples to be evaluated are input into the prediction model.Therefore,it is feasible to build Fisher model based on Gabor characteristics to evaluate and predict the instability degree of muddy submarine channel slope,which is of great significance to the study of channel slope stability.