Wavelet is one of the most outstanding techniques in image processing , and fractal signal processing is a new analysis method developed in past two decades . a study of combining those two methods of signal processing and applying them to image processing is the topic of this thesis 本文对分形这种信号处理中常用的非线性处理技术及其在图像处理中的应用进行了研究，将其与小波变换相结合，用于图像压缩、图像边缘提取、 sar图像消噪等领域，取得了较好的效果。
First , it applies fuzzy logical in the abstract and non - linear dealing ability ; second , it applies neural net in the self - study and any functions approaching ability ? through combining above two ability , it can find a best p i d non - linear controlling regularity and achieve controlling on line of the unknown subject etco therefore , it not only can strengthen robust and intelligence of the system , but also make design simple and easily be requiredo in addition , the thesis also does many works on procedure of upper - computer and basic - controller and the whole system designed can be put into work immediately 根据啤酒发酵过程具有大惯性、时滞和非线性等特点，本论文还提出一种基于神经网络的模糊自适应pid控制方案，它一方面利用模糊逻辑的“概念”抽象能力和非线性处理能力，另一方面利用神经网络的自学习能力和任意函数的逼近能力，通过两者的有机结合寻找一个最佳的p 、 i 、 d非线性组合控制规律，以实现对未知对象进行在线控制，并具备适应控制环境变化的能力和自学习能力等。
The model based on the artificial neural network has advantages of robustness ( the fitting is initial - value - free ) , better fitting precision , strong ability to treat nonlinear model , fast computing , powerful prediction and strong ability to control compared with the conventional linear regression model and the logarithmic regression model 与传统线性回归模型、对数回归模型相比，采用人工神经网络方法建立的模型非线性处理能力强，鲁棒性好，拟合精度高，计算速度快，预测和控制能力强。
If the computation complexity is permitted , we can combine two methods together , which is the improvement trend of noise estimation . there are many speech enhancement techniques , such as filtering , correlation of speech , nonlinear processing , spectrum subtraction , and the adaptive wiener filter 语音增强算法,包括滤波法语音增强、利用相关特性的语音增强、非线性处理语音增强、谱减法语音增强、利用wiener滤波法的语音增强、自适应噪声抵消法语音增强等,我们采用的是目前使用最为广泛的基于短时谱的语音增强算法。
With the characteristics of the task of preprocessing and recognition of underwater acoustic images , the nonlinear methods based on the mathematical morphology was proposed here . the performance of it is better than the conventional methods for the case of suppressing noise , detecting edges and recognition 本文针对水声图象预处理和识别的特殊性，把数学形态学的形态变换应用到“声视觉系统”的预处理和识别中，实现了以数学形态学为理论基础的非线性处理方法，使得图象的去噪、边缘提取和物体识别等处理较传统方法优越和快速。
The radar target identification based on artificial neural network is the protagonist of the chapter 4 . bp network and wavelet network are used to classified the emulational radar targets . with the powerful capability of non - linnear identification of bp neural network , its ’ born limitations such as local extremum , slow convergence etc . can be reformed by the wavelet network , which is a network with a wavelet function embedded into the node of a bp network 研究了基于人工神经网络模型的雷达目标hrrp识别方法。 bp人工神经网络强大的非线性处理能力,在解决复杂目标分类识别时有优势;小波神经网络针对bp网络的不足,将bp网络和小波变换相结合,在网络收敛、网络初始化方面弥补了bp网络的部分缺陷,其识别性能和抗噪性能与bp网络相比有所提高。
When the test is completed p - s curve can be drawn . from the p - s curve , we ca n ' t specify the bearing capacity easily . in order to specify the bearing capacity accuracy , artificial neural network method is used . the fitted p - s curve is approximately accordance with those analyzed by test 论文利用现在较为流行的非线性处理方法? ?人工神经网络方法来拟合p - s曲线，以沉降为标准给出了单桩极限承载力。结果表明，该方法具有良好的处理能力，能够精确的根据p - s曲线给出单桩极限承载力。
In the paper , we describe the whole configuration of the joint transform correlator ; introduce the correlative theories of joint fourier transform in detail ; in order to achieve better correlation result , the nonlinear processing of joint transform power spectrum ( jtps ) is put forward , the effect of jtps laplace sharpening and binary processing to the correlation image is given ; the method of the best binary threshold is determined ; we analyse the correlation image , present the way that removes liquid crystal diffraction spot , direct current spot and image noise , and binarize the correlation image finally 本论文主要对提出的联合变换相关的整体结构进行了描述；详细介绍了联合傅里叶变换的相关理论；为了得到更好的相关结果，本文提出对联合功率谱进行非线性处理的方法，给出了联合变换功率谱的拉普拉斯锐化和谱的二值化处理对相关峰图像的影响及二值化最佳阈值的确定方法；对相关峰图像信息进行了分析；提出了消除液晶衍射光斑、直流光斑和图像噪声的方法；最后对相关峰图像进行了二值化处理。
It not only has great linear and nonlinear solution abilities , provides user developing platforms , such as apdl ( ansys parameter design language ) , uidl ( user interface design ) , upfs ( user routines and non - standard uses ) , etc . in this paper , firstly researching status of reinforced concrete structure strengthened with cfrp is introduced and their advantages and disadvantages is analyzed ; based on it , method is brought forwards , which includes using ansys in fem analysis the structures and to develop a user element 大型通用软件ansys在土木工程上的运用是非常优秀的，具有强大的线性和非线性处理能力；并且提供给用户许多友好的二次开发接口环境，如apdl ( ansysparameterdesignlanguage ) 、 uidl ( userinterfacedesign ) 、 upfs ( userroutinesandnon - standarduses )等。本文首先分析了目前碳纤维布加固钢筋混凝土结构技术研究状况，在此基础上提出了用ansys软件对碳纤维布加固钢筋混凝土梁的机理进行数值分析，并利用ansys的二次开发接口加入了用户单元。
