在车牌字符识别中引入了误识模型和多分类器集成技术。
The techniques of mis-recognition model and multiple classifier combination are proposed and used in the system.
在辩识模型的基础上按最小方差控制原理设计了一离散型自动电压调节器。
On the base of the identified model this paper also presents a discrete automatic voltage regulator by minimum variance control principles.
本文利用递归神经网络来建立异步电机转速辩识模型，其网络学习采用实时递归学习算法。
This paper presents a model for identifying induction motor speed using the recurrent neural network, which is trained by a real time recurrent learning algorithm.
该方法既保证了按照动力学规律描述过程特性，又充分利用现场运行和分析的数据，辩识模型结构参数。
The method not only can describe process attributes according to dynamic rules, but also can make full use of field running and analysis data in order to identify structural parameters.
将人工神经网络的非线性特性和信息的分布性用于煤低温自燃实验炉的模型辩识。
The nonlinearity and distribution of information processing of the artificial neural network are utilized in the indentification of model of coal spontaneous combustion stove at low temperature.
提出了两种类型负荷预报模型，基于建筑模型辩识的负荷预报法和基于时间序列的负荷预报法。
Two kinds of models are derived; load prediction model based on building model recognition and load prediction model based on time series analysis.
其主要特点是能够提供一个跟踪网络来辩识系统模型，进而确定控制器的网络参数，实现间接自适应神经网络控制。
Its major feature is that it can provide a tracing network to identify system model so as to determine the network parameters of the controller and realize an indirect adaptive neural network control.
在说话人辨认实验中，较之传统的GMM方法，基于EGMM的系统的正识率提高了近3%，并且模型具有更小的平均尺寸。
Compared with traditional GMM, the correct recognition rate of si system based on EGMM increases by approximate 3%. Furthermore, the GMMS in new system have smaller average size.
采用新型对角回归神经网络来辩识系统模型，可对PID控制器参数进行整定，实现多变量解耦控制。
Adopting new type diagonal regression neural network to identify the system model, the parameters of PID controller have been set, and the multi -variable decoupling control being realized.
同时给出该类模型中未知参数的辩识方法。
Meanwhile the method of determining the unknown parameters in the model is proposed.
为克服微钙化点检测中假阳性高的缺点，本文构造了一种带拒识能力的双层支持向量模型分类器用于钙化点检测。
To solve the problem of false positive in micro-calcification detection, a double-layer support vector classifier model with reject feature is proposed.
提出了一种传感器动态模型辩识新方法，给出了相应的辩识过程及学习算法。
This paper presents a new method for dynamic model identification of sensors, and gives the corresponding design processes and learning algorithm.
由此可见，裂纹的定量辩识对动力学计算模型和裂纹参数搜索两方面的效率要求非常高，关系到其在工程实际中是否具有应用价值。
It can be seen that the efficiency of the dynamic model and the searching of crack parameters is crucial to the practical application of the quantitative crack identification techniques.
为适应快速识别目标和精确辩识物体的应用需要，提供了这类匹配方法的简易模型和精确模型。
To meet the needs of fast recognizing target and accurately distinguishing object, we propose a simple matching model and an accurate matching model for our method.
基于反问题中的模型参数辩识理论，通过人工神经网络，建立了考虑应力路径影响的粘土的神经网络本构模型。
Based on the model parameter identification theory in inverse problem, a neural network model for constitutive law of clay under multiple stress paths is set up through artificial neural network.
提出了C -R模糊模型的辩识递推算法和C - R模糊模型的非线性预测控制算法。
It is presented the identity conclusion method of C-R fuzzy model and the nonlinear predictive control of C-R fuzzy model.
模型参数估计LS和IVLS法在回旋窑烘干过程的开环辩识中都得到了应用和推广。
Both the LS and the IVLS parameter estimation techniques are successfully tested for open-loop idendification of rotary drying process.
针对不同空间距离和色调障碍物，建立距离判识结果随速度变化的一元线性回归模型及BP神经网络模型；
Study laws of distance discriminating results to red and green obstacles change with velocity at different depths distance and establish a linear regression model and BP neural network model.
基于对多体系统理论，以三轴加工中心误差模型及参数辩识为基础，建立了四轴联动加工中心运动误差模型。
Based on the theory of Multi - body system and the error model and identification of 3-axis machining center, the error mall of 4 - axis machining center is built.
滑动平均模型辩识的困难是信息向量中存在不可测噪声项。
Difficulty of identification of moving average models lie in that unknown noise terms appear in the information vector.
提出了一种用于裂纹辩识的改进型目标函数，并通过免疫智能算法对该目标函数模型进行寻优。
An improved objective function is put forward and the IA is used to solve this optimization problem.
提出了一种用于裂纹辩识的改进型目标函数，并通过免疫智能算法对该目标函数模型进行寻优。
An improved objective function is put forward and the IA is used to solve this optimization problem.
应用推荐