基于在线神经网络的无人机着陆飞行自适应逆控制器设计

基于在线神经网络设计了无人机着陆飞行自适应逆控制器。根据时标分离的原则,将无人机系统分解为快慢不同的四个回路,采用动态逆的方法设计快回路、慢回路和非常慢回路控制器,并且在慢回路和非常慢回路用基于在线神经网络的干扰观测器逼近无人机所受的扰动和动态逆误差,降低了控制器对干扰和模型精确度的要求,增强了控制器的鲁棒性。仿真结果说明所设计的无人机着陆控制器是非常有效的。

小波包分析与BP神经网络预测相结合的在线能量管理策略

针对现有混合储能分配策略无法适应不同储能设备特性以及光伏发电功率信号随机波动特征的问题,提出了将小波包分析,BP神经网络在线预测及模糊控制相结合的分配策略。首先对已有的混储总功率进行小波包分频,得到适合于氢储系统的低频功率,再通过此数据集进行BP神经网络的离线训练,并将训练的权重值用于在线神经网络预测。其次,将在线神经网络训练得到的氢储功率结合超级电容的荷电状态通过模糊控制器得到超级电容功率的修正值,并对氢储设备的功率、在线神经网络的权重进行修正,使得在线神经网络适应实时的混储功率波动。最后根据另一混储功率数据10 s采样数据在MATLAB/Simulink平台进行仿真。与基于规则的混储分配策略和低通滤波的分配策略相比较,结果表明此算法可以很好地改善氢储设备充放电功率,适应实时信号的随机波动,使超级电容的荷电状态运行在合理的区间范围内。

生物发酵过程的在线神经网络逆解耦控制

生物发酵过程具有非线性、多变量耦合的特点。为提高发酵过程解耦控制的性能,提出了一种基于参考模型的在线神经网络逆解耦控制方法。根据发酵过程的特点,给出发酵过程的数学模型和可逆性分析。进一步构造神经网络逆解耦器与被控系统串联,由参考模型输出与被控系统输出的误差设计神经网络连接权值参数的在线学习方法,将被控系统解耦成伪线性系统,最后设计线性闭环控制器获得高性能跟踪控制。仿真结果表明,所提出的方法很好的实现了多变量生物发酵过程的解耦控制,鲁棒性强且结构简单易于工程实现。

基于在线自调整神经网络的最大功率跟踪方法研究

针对扰动观察法易在最大功率点附近振荡的问题,研究基于在线自调整神经网络和扰动观察法结合的最大功率跟踪策略。首先提出可在线调整结构的快速资源优化网络,然后以温度、光伏阵列电压和功率为网络输入,以最大功率点电压为输出,建立MPPT神经网络模型。若当前工作状态与神经网络模型记忆模式距离较近,则以神经网络输出U_N为U_(MPP)。否则,启用扰动观察法在U_N基础上精确定位最大功率点。同时将此运行状态数据作为样本训练调整网络结构,增加记忆模式,提高网络的输出精度。仿真实验证明本方法可避免系统在最大功率点的振荡。

基于神经网络在线学习的脱硝系统入口氮氧化物预测

针对脱硝系统入口氮氧化物静态软测量预测模型不能满足变负荷时需求的问题,建立了一种基于神经网络在线学习的软测量模型.利用粒子群算法对静态神经网络的参数进行寻优,结合预报误差和当前预测误差的大小在线更新网络的权值、阈值和学习速率,可以满足不同负荷下的需求,利用电厂的实际运行数据对模型进行了验证.结果表明:在不同负荷下,建立的神经网络在线学习模型的准确性高,实时性好,泛化能力强,可以很好地对入口氮氧化物进行预测,为脱硝系统入口氮氧化物在线测量和监测提供了一种有效的方法.

基于模型逆神经网络的自主飞行控制系统设计

为满足无人直升机自主飞行要求,设计公共事件服务组件,实现控制组件的分布式通信和控制结构的动态变化;基于模型逆技术,设计某状态下的旋转逆和平移逆控制器,其他状态下的逆误差由在线神经网络补偿.多个机动科目的仿真结果表明:所设计的自主飞行控制系统具有良好的性能,有较大的工程应用价值.

运用在线贯序极限学习机的故障诊断方法

针对传统的前馈神经网络学习算法泛化能力不高、训练速度慢、易出现局部最优解及无法处理随时间不断变化的信息流等问题,提出了基于在线贯序极限学习机的快速故障诊断方法。针对旋转机械故障复杂、样本少的特点,将测试过程中得到的预测数据加入训练样本,作为下一次预测的已知信息,建立在线贯序极限学习机分类模型,从而在最大程度上提高故障诊断的精度。试验结果表明,在线贯序极限学习机在故障分类准确率与支持向量机相近的条件下,参数选择简单且学习速度提高近200倍。

基于神经网络的直升机动态逆飞行控制

传统直升机动态逆控制器包含标称系统动态线性化部分,以及用于实现期望闭环动态的线性控制部分。针对其依赖于直升机精确非线性模型而鲁棒性较差的问题,提出了一种改进的黑鹰UH-60直升机动态逆控制方法,其中逆模型为基于悬停飞行条件下的线性模型。对模型简化、非线性和飞行条件差异所产生的逆误差,引入在线神经网络进行补偿并对系统稳定性进行了分析。非线性仿真结果表明,在不同飞行条件产生的扰动作用下,系统输出响应能够跟踪指定输入,进而说明控制器具有良好的鲁棒性。

神经模糊技术在DSP控制交流调速系统中的应用

运用神经模糊技术中的串联型神经模糊混合模式,设计了神经网络在线模糊自适应控制器,作为异步交流电机直接转矩调速系统中的速度控制器.在TMS320F240 DSP的开发平台上进一步开发设计了全系统的硬件和软件.实验结果表明,系统取得了较好的调速性能.

一种不依赖状态估计的自适应输出反馈控制方法

研究了一种不依赖状态估计的自适应输出反馈控制方法。首先引入伪控制信号使系统反馈线性化 ,然后设计一个线性动态补偿器和在线神经网络 ,自适应消除不确定性和建模所引起的误差。对一含有未建模动态的非线性系统的仿真结果表明 ,该控制方法能够消除系统的稳态误差 ,提高系统动态性能 。

鲁棒自适应飞行跟踪控制系统设计

针对具有外部扰动的一类非线性飞行控制系统提出了一种在线神经网络控制的方法,应用3个在线神经网络分别实时抵消系统中的非线性部分、与控制量耦合的非线性项以及外部扰动,使受控系统的输出可以完全跟踪给定输入参考信号。文中以一个实际的验证机非线性模型为仿真对象,验证了这种方法的有效性,由于在线神经网络的动态补偿特性,即使飞机在不同的高度和速度下,在模型参数发生改变时,控制过程并不需要改变增益表就可以完成全包络的飞行跟踪控制,相关的定理证明了整个神经自适应飞行闭环控制系统的稳定性,仿真示例表明了该设计方法的有效性。

基于RBF和动态配平的高速直升机边界保护控制

以复合共轴双旋翼高速直升机为研究对象,针对直升机模态下低速前飞时飞行姿态边界保护问题,提出一种基于指令受限的安全保护控制方法。首先,建立高速直升机全模态非线性数学模型;然后,以低速前飞时的俯仰角保护为例,运用受限参数的动态响应估计以及动态配平算法实现指令边界预测,从而对控制输入指令进行安全优化修正。仿真结果表明:本控制方法可以对高速直升机飞行边界进行保护,有效提升飞行的安全性和可靠性。

On-line Fault Diagnosis in Industrial Processes Using Variable Moving Window and Hidden Markov Model

An integrated framework is presented to represent and classify process data for on-line identifying abnormal operating conditions. It is based on pattern recognition principles and consists of a feature extraction step, by which wavelet transform and principal component analysis are used to capture the inherent characteristics from process measurements, followed by a similarity assessment step using hidden Markov model (HMM) for pattern comparison. In most previous cases, a fixed-length moving window was employed to track dynamic data, and often failed to capture enough information for each fault and sometimes even deteriorated the diagnostic performance. A variable moving window, the length of which is modified with time, is introduced in this paper and case studies on the Tennessee Eastman process illustrate the potential of the proposed method.

RVFLN-based online adaptive semi-supervised learning algorithm with application to product quality estimation of industrial processes

Direct online measurement on product quality of industrial processes is difficult to be realized,which leads to a large number of unlabeled samples in modeling data.Therefore,it needs to employ semi-supervised learning(SSL)method to establish the soft sensor model of product quality.Considering the slow time-varying characteristic of industrial processes,the model parameters should be updated smoothly.According to this characteristic,this paper proposes an online adaptive semi-supervised learning algorithm based on random vector functional link network(RVFLN),denoted as OAS-RVFLN.By introducing a L2-fusion term that can be seen a weight deviation constraint,the proposed algorithm unifies the offline and online learning,and achieves smoothness of model parameter update.Empirical evaluations both on benchmark testing functions and datasets reveal that the proposed OAS-RVFLN can outperform the conventional methods in learning speed and accuracy.Finally,the OAS-RVFLN is applied to the coal dense medium separation process in coal industry to estimate the ash content of coal product,which further verifies its effectiveness and potential of industrial application.

Neural Network for Prediction of Thermal Elastomer Quality

Aim To predict the indexes of quality of the thermal elastomer by polymerization process data. Methods Neural networks were used for learning the relationship between the product quality and the polymerization process condition variables in an industrial scale batch polymerization reactor. Results The indexes of quality of the product were inferred with acceptable accuracy from easy to measure reaction process condition variables. Conclusion The method proposed in this paper provides on line soft sensors of the indexes of quality of the thermal elastomal.

A New Strategy of Integrated Control and On-line Optimization on High-purity Distillation Process

For high-purity distillation processes,it is difficult to achieve a good direct product quality control using traditional proportional-integral-differential(PID)control or multivariable predictive control technique due to some difficulties,such as long response time,many un-measurable disturbances,and the reliability and precision issues of product quality soft-sensors.In this paper,based on the first principle analysis and dynamic simulation of a distillation process,a new predictive control scheme is proposed by using the split ratio of distillate flow rate to that of bottoms as an essential controlled variable.Correspondingly,a new strategy with integrated control and on-line optimization is developed,which consists of model predictive control of the split ratio,surrogate model based on radial basis function neural network for optimization,and modified differential evolution optimization algorithm. With the strategy,the process achieves its steady state quickly,so more profit can be obtained.The proposed strategy has been successfully applied to a gas separation plant for more than three years,which shows that the strategy is feasible and effective.

A cellular wireless location algorithm based on RON online RBF neural network

A location and tracking algorithm with NLOS （Non-Line of Sight） errors for MS （Mobile Station） is proposed in this paper. A cellular localization algorithm based on the RON online RBF neural network is proposed. The measurement ofAOA, TOA and TDOA provided by mobile base station is fused to locate mobile. The location performance of RON online RBF neural network is simulated. The simulation results indicate that shrink, attenuation, shift or overlapping phenomenon is avoided when the network redundant hidden nodes appear. It＇ s location accuracy is significantly improved under complicated multi-path environment.

Convergence of On-Line Gradient Methods for Two-Layer Feedforward Neural Networks

A discussion is given on the convergence of the on-line gradient methods for two-layer feedforward neural networks in general cases. The theories are applied to some usual activation functions and energy functions.

Finite Convergence of On-line BP Neural Networks with Linearly Separable Training Patterns

In this paper we prove a finite convergence of online BP algorithms for nonlinear feedforward neural networks when the training patterns are linearly separable.