一种基于AFSA的神经网络投影寻踪耦合回归模型

人工鱼群算法是通过模仿鱼群的觅食、聚群和追尾等行为寻找最佳觅食水域从而实现全局寻优的优化算法。应用神经网络的投影寻踪耦合回归模型存在优化问题,学习过程中运用人工鱼群算法进行优化,进而获得最佳的投影方向、阈值和正交Hermite多项式系数。本文描述了应用人工鱼群算法优化的神经网络投影寻踪耦合回归模型算法。仿真实验结果表明,该算法可以获得满意的预测效果。     

基于SAPSO算法的非线性预测控制方法研究

神经网络模型在非线性系统预测控制中得到广泛地应用,但是存在预测控制律难以求取的问题,文章提出模拟退火粒子群优化(SAPSO)算法来进行优化求解。在对PSO算法与SAPSO算法进行分析的基础上,采用SAPSO优化算法对神经网络预测控制策略进行了优化,再通过仿真实验对PSO算法与SAPSO算法的预测性能进行了比较。仿真结果表明SAPSO优化算法能有效减少迭代次数、提高收敛精度。     

基于FOA优化GRNN的船舶交通流预测模型

针对船舶交通流预测中存在复杂性、非线性、受限因素多等特点,运用果蝇优化算法,建立了优化的广义回归神经网络船舶交通流预测模型。通过利用果蝇优化算法的全局寻优特性对广义回归神经网络进行参数优化,从而实现对船舶交通流的预测。以东海大桥的船舶流量观测数据为实例对象进行分析,通过MATLAB进行仿真预测,实验结果表明:FOA-GRNN模型相比于传统的GRNN模型和BPNN模型具有更高的预测精度和泛化能力,有效地解决了预测过程中数据样本少、非线性拟合能力差等问题,对水路的规划、通航管理等方面具有一定的应用价值。     

基于混合改进GSO与GRNN并行集成学习模型

针对萤火虫群优化算法(GSO)不稳定、收敛速度较慢与收敛精度较低等问题和广义回归神经网络(GRNN)的网络结构导致预测误差的特性,提出基于混合改进萤火虫群算法与广义回归神经网络并行集成学习模型,应用于雾霾预测.首先构建融合多种搜索策略的混合改进萤火虫群优化算法(HIGSO),并使用标准测试函数验证算法性能.然后结合HIGSO与引入扰动因子的GRNN模型,建立并行集成学习模型,并通过UCI标准数据集验证模型的有效性与可行性.最后将模型应用于北京、上海和广州地区的雾霾预测,进一步验证模型在雾霾预测中的性能.     

非线性时滞系统双阶段神经网络的改进广义预测控制

针对一类工业控制系统中存在的非线性、大时滞等情况,提出一种基于双阶段神经网络的改进隐式广义预测控制方法。首先,设计了一种基于快速回归算法和蝙蝠算法的双阶段神经网络模型,用于对非线性时滞系统进行建模,避免非线性系统下的模型失配问题;其次,采用比例积分(proportional integration, PI)结构优化广义预测控制目标函数设计,提高隐式广义预测控制性能;同时,改进控制增量选取策略,利用所预测的未来控制增量修正当前时刻控制增量;最后,将所设计的预测模型和预测控制方法应用于一个数值案例和锅炉燃烧系统,验证了所提控制策略的有效性。     

基于FOA-GRNN油井计量原油含水率的预测

研究原油含水率准确预测问题,提供高精度的原油含水率数据在油井计量中具有重要意义。针对原油含水率预测受到多因素影响,由于原油中存在复杂的非线性关系,传统的预测方法无法满足预测精度要求。为了提高原油含水率的预测精度,提出了果蝇优化广义回归神经网络的原油含水率预测方法,果蝇优化算法用于广义回归神经网络的参数优化。通过同轴线相位法含水率计的测量系统对原油含水率有影响的多个参量进行测定,建立果蝇算法优化广义回归神经网络的原油含水率预测模型。仿真结果表明:相对于广泛应用的BPNN预测模型,果蝇算法优化的广义回归神经网络预测精度高,是一种实用有效的原油含水率预测方法。     

基于WNN的两种优化结果在预测控制中的应用*

从优化小波神经网络的角度出发,对两种优化模型从理论上进行建模与推导;根椐预测控制的特点,提出离散小波神经网络模型GA分层优化方法及广义小波神经网络模型优化方法与预测控制相结合的新的应用途径.仿真结果证明了该方法的有效性和可行性,能使实际工程中的预测控制结果得到优化.     

蚁群算法在需水预测模型参数优化中的应用

为了解决投影寻踪（PP）需水预测模型的高维、非正态、非线性参数优化问题,提高需水预测的精度,尝试用基于网格划分的自适应连续域蚁群算法(ACA)在不同拟合和预测时长内对模型参数进行优化组合,并运用该模型进行年需水量预测。基于改进蚁群算法的投影寻踪需水预测模型参数优化进行了实例仿真。对基于改进蚁群算法的预测精度与基于人工免疫算法（AIA）和BP神经网络的模型(BPANN)参数优化结果分别进行了比较,实验结果表明：1）这三种算法的拟合精度相对误差绝对值分别小于2%、10%和10%;2）预测精度相对误差绝对值分别小于6%、11%和12%;3）改进蚁群算法能收敛到全局最优解,收敛速度较快。因此,改进蚁群算法的投影寻踪需水预测结果明显优于人工免疫算法和BP神经网络。该方法可推广到其他类似的高维非线性问题上。     

基于遗传算法优化投影寻踪技术的神经网络集成模型及其应用

首先利用遗传算法优化的投影寻踪技术对神经网络学习矩阵降维,再利用Bagging技术和不同的神经网络学习算法生成集成个体,并再次用遗传算法进化的投影寻踪技术对神经网络个体集成.建立基于遗传算法优化的投影寻踪技术神经网络集成模型,通过上证指数开盘价、收盘价进行实例分析,计算结果表明该方法具有较好的学习能力和泛化能力,在股市预测中预测精度高、稳定性好.     

修正型果蝇算法优化GRNN网络的尾矿库安全预测

针对尾矿库事故具有随机波动性和非线性的特点,提出采用修正型果蝇优化算法优化广义回归神经网络的尾矿库安全评价模型( MFOA-GRNN)。该方法利用修正型果蝇优化算法的全局寻优特性对广义回归神经网络进行参数优化,同时应用去相关性分析选取尾矿库安全评价指标,实现尾矿库的安全预测。以辽宁本溪南芬尾矿库为研究实例进行拟合预测,实验结果表明,将MFOA方法与GRNN网络有机结合,有利于平滑因子σ的选择,相较于FOA-GRNN模型70%的预测准确度,采用修正型果蝇算法优化的GRNN模型预测准确度高达100%,预测精度更高,适用性更强。     

Nonlinear system identification for predictive control using continuous time recurrent neural networks and automatic differentiation

In this paper, a continuous time recurrent neural network (CTRNN) is developed to be used in nonlinear model predictive control (NMPC) context. The neural network represented in a general nonlinear state-space form is used to predict the future dynamic behavior of the nonlinear process in real time. An efficient training algorithm for the proposed network is developed using automatic differentiation (AD) techniques. By automatically generating Taylor coefficients, the algorithm not only solves the differentiation equations of the network but also produces the sensitivity for the training problem. The same approach is also used to solve the online optimization problem in the predictive controller. The proposed neural network and the nonlinear predictive controller were tested on an evaporation case study. A good model fitting for the nonlinear plant is obtained using the new method. A comparison with other approaches shows that the new algorithm can considerably reduce network training time and improve solution accuracy. The CTRNN trained is used as an internal model in a predictive controller and results in good performance under different operating conditions.     

一类非线性系统的神经网络预测控制

针对一类具有特殊模型的非线性系统本文提出了一种新型神经网络预测控制算法。该算法利用线性系统预测控制技术和神经网络的非线性映射及并行处理能力来求实际控制量，避免了解非线性方程和非线性预测控制所需的在线数值寻优计算，减少了计算量和计算时间。仿真结果表明了该算法的何效性。     

神经网络预测控制局部优化初值确定方法

为解决局部优化算法初值选取不当造成神经网络预测控制性能下降的问题,本文提出了一种动态确定初值的方法.在每次优化时通过逆网络将初值选在输出误差最小点,通过修正目标性能函数中的权重因子来确保初值与当前控制量之间存在极值,并在理论上进行了证明.以BP神经网络预测控制为例,采用牛顿拉夫逊算法实现滚动优化,对所提方法进行了仿真实验,结果表明能够解决初值问题,提高控制系统的可靠性.     

A general projection neural network for solving monotone variational inequalities and related optimization problems

Recently, a projection neural network for solving monotone variational inequalities and constrained optimization problems was developed. In this paper, we propose a general projection neural network for solving a wider class of variational inequalities and related optimization problems. In addition to its simple structure and low complexity, the proposed neural network includes existing neural networks for optimization, such as the projection neural network, the primal-dual neural network, and the dual neural network, as special cases. Under various mild conditions, the proposed general projection neural network is shown to be globally convergent, globally asymptotically stable, and globally exponentially stable. Furthermore, several improved stability criteria on two special cases of the general projection neural network are obtained under weaker conditions. Simulation results demonstrate the effectiveness and characteristics of the proposed neural network.     

基于集成模型与遍历搜索算法的铅锌烧结透气性优化

以铅锌烧结过程为研究对象,针对烧结过程透气性的控制问题,提出了基于集成预测模型与遍历优化搜索算法的铅锌烧结透气性优化控制方法.首先采用优化组合集成技术将神经网络预测模型和灰色系统预测模型有机结合,建立烧结综合透气性集成预测模型,然后结合14# 风箱温度和烧穿点温度建立透气性状况综合评判模型,最后通过遍历优化搜索算法,获得二配配比和混合料水分设定值,并进行跟踪控制,从而实现烧结过程透气性的优化控制.仿真结果表明:该方法能有效改善烧结过程的透气性.稳定烧结过程.     

Constrained multi-variable generalized predictive control using a dual neural network

Multi-variable generalized predictive control algorithm has obtained great success in process industries. However, it suffers from a high computational cost because the multi-stage optimization approach in the algorithm is time-consuming when constraints of the control system are considered. In this paper, a dual neural network is employed to deal with the multi-stage optimization problem, and bounded constraints on the input and output signals of the control system are taken into account. The dual neural network has many favorable features such as simple structure, rapid execution, and easy implementation. Therefore, the computation efficiency, in comparison with the consecutive executions of numerical algorithms on digital computers, is increased dramatically. In addition, the dual network model can yield the exact optimum values of future control signals while many other neural networks only obtain the approximate optimal solutions. Hence the multi-variable generalized predictive control algorithm based on the dual neural network is suitable for industrial applications with the real-time computation requirement. Simulation examples are given to demonstrate the efficiency of the proposed approach.     

Optimal disturbance rejection control approach based on a compound neural network prediction method

A new optimal disturbance rejection control method is proposed for the system with disturbances via a compound neural network prediction approach in this paper. The disturbances caused by external disturbances and model mismatches can be estimated by a disturbance observer, and the estimation of disturbances is introduced into the neural network predictive model to make the predictive output more accurate. Then based on the new compound neural network predictive model, a controller, which ensures both optimal performance by the receding horizon optimization and strong disturbance rejection ability, is obtained. The proposed scheme is applied to control the temperature of a simplified jacketed stirred tank heater (JSTH). Simulation results demonstrate the effectiveness of the proposed control method.     

Constructive learning neural network applied to identification and control of a fuel-ethanol fermentation process

In the present work, a constructive learning algorithm was employed to design a near-optimal one-hidden layer neural network structure that best approximates the dynamic behavior of a bioprocess. The method determines not only a proper number of hidden neurons but also the particular shape of the activation function for each node. Here, the projection pursuit technique was applied in association with the optimization of the solvability condition, giving rise to a more efficient and accurate computational learning algorithm. As each activation function of a hidden neuron is defined according to the peculiarities of each approximation problem, better rates of convergence are achieved, guiding to parsimonious neural network architectures. The proposed constructive learning algorithm was successfully applied to identify a MIMO bioprocess, providing a multivariable model that was able to describe the complex process dynamics, even in long-range horizon predictions. The resulting identification model was considered as part of a model-based predictive control strategy, producing high-quality performance in closed-loop experiments.     

微分改进RBF网络线性预测控制算法的研究

针对现有非线性系统辨识超调较大和预测控制计算量繁琐等问题,提出了改进的RBF神经网络线性预测控制算法.该方法通过在传统性能指标函数中增加误差微分项,以优化跟踪效果;利用辨识模型作为预测模型,对输出设定值进行线性逼近的反向优化,并实时给出优化控制量.该方法简化了传统预测控制算法,在加快寻优速度的同时,有效地抑制了超调.通过非线性系统仿真实例,验证了该方法的可行性和有效性.