基于虚拟仪器的表面肌电信号特征提取算法的研究

提出一种基于虚拟仪器的表面肌电信号的特征提取算法。该方法利用虚拟仪器丰富的函数功能,针对肌电信号的非平稳性特征,应用积分阈值法首先去除静息电位,保留最有价值的信号部分,然后利用小波包变换的方法对肌电信号进行小波包分解,根据其投影到不同频段上小波包系数能量的不同,利用能量较大的几组系数重构肌电信号。实验结果表明:该方法能有效地去除静息电位及噪声信号,且保留了肌电信号的细节信息,为肌电信号的模式识别创造了良好的条件。该研究依据虚拟仪器平台,为创建表面肌电信号实时控制机械臂系统提供了研究基础,具有潜在的工程应用价值。     

平整机轧制力阶跃奇异点的小波检测与分析

轧制力阶跃奇异点是对平整机轧制力控制系统进行故障诊断和系统分析的一类重要数据,采用小波分析方法对平整机轧制力控制系统阶跃奇异点进行检测、定位和分析.对奇异点检测的小波分析方法进行探讨,确定了用于轧制力阶跃奇异点检测的小波基函数.通过采用小波阶跃奇异点检测方法对某平整机实际轧制力数据进行阶跃奇异点的检测和定位,论证了该方法的正确性.     

基于小波分析的油气管道缺陷磁记忆检测研究

金属磁记忆检测技术是目前唯一能对铁磁性构件早期损伤进行诊断的无损检测手段,能检测识别油气管道早期损伤以及以应力集中为特征的裂纹缺陷。小波分析由于具有良好的时频局部性,能很好地克服傅里叶变换的不足,得到广泛的应用。针对目前金属磁记忆检测技术以过零点作为缺陷判定准则存在的不足,利用小波尺度谱和再分配的尺度谱对磁记忆信号进行分析。试验结果表明,小波再分配尺度谱能有效应用于管道缺陷的磁记忆检测之中。     

基于小波一阶灰度矩向量和神经网络的旋转机械故障诊断的研究

在旋转机械轴系振动故障模拟试验的基础上,对大量故障模拟试验数据进行计算,建立了典型故障的小波一阶灰度矩向量样本,将其作为概率神经网络的输入进行故障诊断研究。结果表明,基于一阶灰度矩向量的概率神经网络可实现对训练样本100%的正确识别率,对陌生样本的正确识别率也超过75%。可见,概率神经网络综合了Bayes分类器和神经网络的优势,利用概率神经网络融合信号的一阶灰度矩向量特征实现旋转机械轴系故障模式识别是一种可行有效的方法。     

基于小波时间序列模型的磨加工尺寸预测技术研究

磨削加工是高精密零件的重要加工环节,且影响磨削工件尺寸精度的因素复杂。针对传统预测模型无法准确预测其趋势变化或预测效果较差,且预测精度不高这一问题,通过对磨加工过程进行分析,对尺寸预测技术的适用性进行研究,提出将小波变换与时间序列分析相结合的预测模型。通过实验验证小波时间序列模型预测平均误差不超过1μm,平均绝对误差MAE=0.105,均方根误差RMSE=0.185,平均绝对百分比误差MAPE=0.159,证明了基于小波时间序列模型的磨加工尺寸预测技术的精确性与可行性。     

基于小波变换的图像边缘检测

介绍了利用小波变换进行图像边缘检测的原理与方法。基于小波变换的模极大值原理,利用不同尺度小波变换后的不同方向获取图像的高频信息,并通过小波系数的模极值点与过零点,检测出图像在四个方向上的模极大值,得到该位置模的局部最大值。仿真测试表明,利用小波变换进行图像边缘检测可以较好的检测图像边缘的细节特征,取得了很好的效果。     

Airplane extraction and identification by improved PCNN with wavelet transform and modified Zernike moments

At an airport, the information of the number and positions of airplanes is very important for the applications of air navigation. Especially, the information from airplane extraction and identification is significant in both civil and military remote sensing. In this paper, according to the characteristics of airplanes and airport in satellite remote sensing images, a new airplane image segmentation algorithm is proposed based on improved pulse-coupled neural network (PCNN) with wavelet transform, and airplane identification algorithm is carried out by using modified Zernike moments. Firstly, for an original image, a PCNN model is improved and then used to do image segmentation by combining the wavelet transform. Then, in order to reduce the number of irrespective targets in the image and increase the processing speed, the airplanes in the original image are roughly detected on the characteristics of the segmented object contour geometries. Finally, the Zernike moments are modified and then applied to identify the roughly detected airplanes accurately. By comparing to the five traditional image segmentation algorithms for the same airplane images, the testing results show that the improved PCNN image segmentation algorithm can segment and detect airplane regions at an airport accurately at a high recognising rate and with high recognising stability, and it is not affected by the image shadows and rotations.     

A model to identify high crash road segments with the dynamic segmentation method

Currently, high social and economic costs in addition to physical and mental consequences put road safety among most important issues. This paper aims at presenting a novel approach, capable of identifying the location as well as the length of high crash road segments. It focuses on the location of accidents occurred along the road and their effective regions. In other words, due to applicability and budget limitations in improving safety of road segments, it is not possible to recognize all high crash road segments. Therefore, it is of utmost importance to identify high crash road segments and their real length to be able to prioritize the safety improvement in roads. In this paper, after evaluating deficiencies of the current road segmentation models, different kinds of errors caused by these methods are addressed. One of the main deficiencies of these models is that they can not identify the length of high crash road segments. In this paper, identifying the length of high crash road segments (corresponding to the arrangement of accidents along the road) is achieved by converting accident data to the road response signal of through traffic with a dynamic model based on the wavelet theory. The significant advantage of the presented method is multi-scale segmentation. In other words, this model identifies high crash road segments with different lengths and also it can recognize small segments within long segments. Applying the presented model into a real case for identifying 10–20 percent of high crash road segment showed an improvement of 25–38 percent in relative to the existing methods.     

基于小波变换的边缘保留图像去噪改进算法

针对在图像去噪过程中,如何有效地保留图像边缘等重要特征信息的问题,提出了一种基于小波变换的图像去噪改进算法。对图像进行多尺度小波分解,将各子带小波系数进行自适应阈值化处理,边缘成分的阈值由子带阈值和给定的相关权重计算得到,从而有效保留图像边缘信息。分别对Tracy和Building图像进行处理,实验结果表明,与BayesShrink等4种传统方法相比较,改进算法不仅可以有效去除不同程度的加性高斯白噪声,很好地保留图像边缘等重要特征信息,而且具有较高的峰值信噪比。