Fuzzy Shape Control Based on El man Dynamic Recursion Network Prediction Model

In the strip rolling process, shape control system possesses the characteristics of nonlinearity, strong coupling, time delay and time variation. Based on self adapting Elman dynamic recursion network prediction model, the fuzzy control method was used to control the shape on four-high cold mill. The simulation results showed that the system can be applied to real time on line control of the shape.

Target threat estimation based on discrete dynamic Bayesian networks with small samples

The accuracy of target threat estimation has a great impact on command decision-making.The Bayesian network,as an effective way to deal with the problem of uncertainty,can be used to track the change of the target threat level.Unfortunately,the traditional discrete dynamic Bayesian network(DDBN)has the problems of poor parameter learning and poor reasoning accuracy in a small sample environment with partial prior information missing.Considering the finiteness and discreteness of DDBN parameters,a fuzzy k-nearest neighbor(KNN)algorithm based on correlation of feature quantities(CF-FKNN)is proposed for DDBN parameter learning.Firstly,the correlation between feature quantities is calculated,and then the KNN algorithm with fuzzy weight is introduced to fill the missing data.On this basis,a reasonable DDBN structure is constructed by using expert experience to complete DDBN parameter learning and reasoning.Simulation results show that the CF-FKNN algorithm can accurately fill in the data when the samples are seriously missing,and improve the effect of DDBN parameter learning in the case of serious sample missing.With the proposed method,the final target threat assessment results are reasonable,which meets the needs of engineering applications.

A Statistical Parameter Analysis and SVM Based Fault Diagnosis Strategy for Dynamically Tuned Gyroscopes

Gyro's fault diagnosis plays a critical role in inertia navigation systems for higher reliability and precision. A new fault diagnosis strategy based on the statistical parameter analysis (SPA) and support vector machine (SVM) classification model was proposed for dynamically tuned gyroscopes (DTG). The SPA, a kind of time domain analysis approach, was introduced to compute a set of statistical parameters of vibration signal as the state features of DTG, with which the SVM model, a novel learning machine based on statistical learning theory (SLT), was applied and constructed to train and identify the working state of DTG. The experimental results verify that the proposed diagnostic strategy can simply and effectively extract the state features of DTG, and it outperforms the radial-basis function (RBF) neural network based diagnostic method and can more reliably and accurately diagnose the working state of DTG.

Identification of Artificial Neural Network Models for Three-Dimensional Simulation of a Vibration-Acoustic Dynamic System

Industrial noise can be successfully mitigated with the combined use of passive and Active Noise Control (ANC) strategies. In a noisy area, a practical solution for noise attenuation may include both the use of baffles and ANC. When the operator is required to stay in movement in a delimited spatial area, conventional ANC is usually not able to adequately cancel the noise over the whole area. New control strategies need to be devised to achieve acceptable spatial coverage. A three-dimensional actuator model is proposed in this paper. Active Noise Control (ANC) usually requires a feedback noise measurement for the proper response of the loop controller. In some situations, especially where the real-time tridimensional positioning of a feedback transducer is unfeasible, the availability of a 3D precise noise level estimator is indispensable. In our previous works [1,2], using a vibrating signal of the primary source of noise as an input reference for spatial noise level prediction proved to be a very good choice. Another interesting aspect observed in those previous works was the need for a variable-structure linear model, which is equivalent to a sort of a nonlinear model, with unknown analytical equivalence until now. To overcome this in this paper we propose a model structure based on an Artificial Neural Network (ANN) as a nonlinear black-box model to capture the dynamic nonlinear behaveior of the investigated process. This can be used in a future closed loop noise cancelling strategy. We devise an ANN architecture and a corresponding training methodology to cope with the problem, and a MISO (Multi-Input Single-Output) model structure is used in the identification of the system dynamics. A metric is established to compare the obtained results with other works elsewhere. The results show that the obtained model is consistent and it adequately describes the main dynamics of the studied phenomenon, showing that the MISO approach using an ANN is appropriate for the simulation of the investigated process. A clear conclusion is reached highlighting the promising results obtained using this kind of modeling for ANC.

基于事件触发的预设时间航天器轨迹跟踪控制

针对通信受限条件下的航天器轨迹跟踪问题,提出了一种基于事件触发的预设时间控制算法。为了满足不同任务场景下对航天器快速性的要求,本文设计了一种预设时间轨迹跟踪控制算法。结合反步控制理论及预设时间动态增益,最终实现轨迹跟踪系统的预设时间收敛。作为一种典型的网络化控制系统,航天器在执行任务过程中可能会受到自身通信能力的限制,造成通信阻塞、时延和丢包等问题。为此,本文提出了一种基于动态参数的事件触发算法,在保证系统控制精度的同时,一定程度上避免了控制中心与航天器本体间不必要的通信资源消耗。相比于传统的静态事件触发算法,文中基于动态参数的事件触发算法在减少通信频率方面更具优势。通过理论分析和仿真实验验证所提控制算法的有效性。

基于BPNN和MOOGA的高速联轴器多目标优化方法

针对高转速、复合工况下膜盘联轴器难以保证其强度特性问题,对已有膜盘联轴器强度及动力学特性进行了研究,提出了一种基于反向传播神经网络(BPNN)和多目标优化遗传算法(MOOGA)的高速联轴器多目标优化方法。首先,为了得到优化所需的关键参数,采用了正交实验结合多因素方差分析的方法,选取了联轴器优化参数;然后,基于已选取的关键参数,采用BPNN方法构建了截面应力和弯曲刚度的目标函数,并将其与多项式拟合方法进行了对比,对BPNN方法的精确性进行了验证;最后,采用MOOGA方法对目标函数进行了多目标优化,并将优化前后结果进行了对比分析。研究结果表明:采用BPNN结合MOOGA的方法对联轴器设计参数进行优化,在满足联轴器刚度需求的情况下,可有效降低联轴器膜盘的危险截面应力;优化后,联轴器危险应力减小了18.2%,弯曲刚度降低了5.05%,联轴器角向补偿能力增加了0.1°,从而证明了仿真的有效性。该结果可以为挠性联轴器参数优化设计提供参考。

Aircraft parameter estimation using a stacked long short-term memory network and Levenberg-Marquardt method

To effectively estimate the unknown aerodynamic parameters from the aircraft’s flight data,this paper proposes a novel aerodynamic parameter estimation method incorporating a stacked Long Short-Term Memory(LSTM)network model and the Levenberg-Marquardt(LM)method.The stacked LSTM network model was designed to realize the aircraft dynamics modeling by utilizing a frame of nonlinear functional mapping based entirely on the measured input-output data of the aircraft system without requiring explicit postulation of the dynamics.The LM method combines the already-trained LSTM network model to optimize the unknown aerodynamic parameters.The proposed method is applied by using the real flight data,generated by ATTAS aircraft and a bio-inspired morphing Unmanned Aerial Vehicle(UAV).The investigation reveals that for the two different flight data,the designed stacked LSTM network structure can maintain the efficacy of the network prediction capability only by appropriately adjusting the dropout rates of its hidden layers without changing other network parameters(i.e.,the initial weights,initial biases,number of hidden cells,time-steps,learning rate,and number of training iterations).Besides,the proposed method’s effectiveness and potential are demonstrated by comparing the estimated results of the ATTAS aircraft or the bio-inspired morphing UAV with the corresponding reference values or wind-tunnel results.

深层页岩气井气水两相缝网参数反演方法

深层页岩气藏的开发离不开大规模的体积压裂技术,而缝网参数反演方法是压裂效果评价、产能动态分析的一种重要手段。现有的缝网参数反演方法忽略了支撑剂不均匀分布和气水两相渗流对深层页岩气藏开发的影响,导致参数反演误差较大,且难以区分“近井支撑裂缝”和“远井未支撑裂缝”对产能的贡献。针对这一问题,基于动态分析方法,建立了考虑多重非线性流动机理和未完全支撑裂缝的深层页岩储层气水两相缝网参数反演方法。反演方法建立过程中基于线性流模型假设,将压后的复杂裂缝网络等效为支撑裂缝区、压裂改造内区、未支撑裂缝区和压裂改造外区4个区域,采用变量替换、摄动变换、逐次替换等手段处理气体高压物性参数、超临界吸附、应力敏感、非达西渗流和气水两相渗流引起的非线性。利用数值模拟模型验证了本文方法的可靠性,并选取四川盆地4口深层页岩气井进行了应用分析。结果表明,建立的深层页岩气水两相缝网参数反演方法考虑了气液同产对产能预测和参数反演的影响,实现了支撑与未支撑裂缝半长和渗透率等参数的定量区分,为准确计算深层页岩气产量、评价压裂效果提供了理论指导。

用于训练神经网络的自适应梯度下降优化算法

由于神经网络规模的扩大,模型训练变得越来越困难.为应对这一问题,提出了一种新的自适应优化算法——Adaboundinject.选取Adam的改进算法Adabound算法,引入动态学习率边界,实现了自适应算法向随机梯度下降(SGD)的平稳过渡.为了避免最小值的超调,减少在最小值附近的振荡,在Adabound的二阶矩中加入一阶矩,利用短期参数更新作为权重,以控制参数更新.为了验证算法性能,在凸环境下,通过理论证明了Adaboundinject具有收敛性.在非凸环境下,进行了多组实验,采用了不同的神经网络模型,通过与其他自适应算法对比,验证了该算法相比其他优化算法具有更好的性能.实验结果表明,Adaboundinject算法在深度学习优化领域具有重要的应用价值,能够有效提高模型训练的效率和精度.

振动能量收集中的动态效率优化神经网络算法应用

动态效率优化神经网络算法(DEONN)的提出旨在提高振动能量收集设备的能量转换效率。DEONN利用深度学习技术,结合多层感知器架构,优化了发电机的关键组件(电枢、换向器、刷子、磁场及外壳)参数,提升了能量转换效率。开展实验实现该算法预测不同运行条件下的电机效率,具体为通过建立一个包含隐藏层的神经网络,输入转速、负载电阻和线圈数等特征,预测不同工况下的电机效率。实验结果表明,实测效率与预测效率具有高度一致性,预测效率为88.5%,验证了DEONN在预测发电机的转速、负载电阻和线圈数等关键性能参数方面的有效性。

基于事件触发机制的动力定位系统神经自适应控制

针对含模型参数不确定和环境干扰的水面船动力定位控制问题,本文提出了一种基于事件触发机制的神经自适应控制算法。结合径向基函数神经网络和最小学习参数算法设计自适应项补偿环境干扰和模型参数不确定。设计的自适应项仅有3个在线学习参数,减少了传统神经网络自适应技术的参数学习个数。再结合动态面控制技术和事件触发机制设计动力定位控制器,其中引入一种事件触发机制降低控制器到执行机构的信息传输负担,同时降低执行机构的动作次数。使用Lyapunov稳定性理论证明了闭环系统的稳定性。通过仿真试验和对比分析验证了提出控制律的有效性。

遗传神经网络下机器人双头夹具参数优化研究

由于直角坐标机器人双头夹具动力学较为复杂,难以找到双头夹具最优参数组合,因此以直角坐标机器人为基础,提出遗传神经网络下机器人双头夹具参数优化方法。分析不同工况下双头夹具关节在夹持工件时的接触力,结合偏移量约束搭建双头夹具动力学模型。以动力学模型为基础,设置参数优化约束条件,包括竖直与水平移动距离、末端节点运行速度、夹具质量、等效应力、丝杠变形量等。结合相关约束条件,构建双头夹具参数优化目标函数,利用遗传神经网络对目标函数进行求解,获取目标函数最优解,该解即为双头夹具参数结果。经实验数据分析证明,所提方法优化后的双头夹具参数更接近于理想值,夹具灵敏度更高,能够有效提升其工作质量。

基于神经网络算法的等离子体负载动态参数模型

等离子体负载电学模型大多基于固定参数模型,忽略了负载等效参数变化对模型的影响,容易产生较大误差。为了改善因等效参数变化带来的误差,首先探究了等效电容、等效电阻等负载参数随外加电压幅值、频率的变化情况,据此训练了BP神经网络参数调整模块,建立了等离子体负载动态参数模型,实现了外施激励变化下负载等效参数的更新。结果表明,采用神经网络动态参数模型仿真精度为95.70%,而采用固定参数模型仿真精度为82.89%,仿真精度提高了15.45%。对简化实验工作量、指导等离子体反应器设计有着重要意义。

基于神经网络的薄壁件铣削动力学参数预测

精确预测薄壁件铣削过程中工件的时变动力学参数是选择无颤振切削参数的基础。本文提出了基于三层神经网络的曲面薄壁件铣削时变动力学参数的预测方法。首先利用壳单元将薄壁件进行离散化,将离散单元结点处工件厚度作为输入参数,工件前三阶固有频率作为输出参数,构建三层神经网络。然后将壳单元有限元模型计算结果作为训练样本,训练得到神经网络模型。模态测试实验结果表明,有限元模型对工件固有频率预测的最大误差约为4%;与有限元模型相比,神经网络模型的最大预测误差为0.409%,因此神经网络模型的最大预测误差约为4%。同时,神经网络模型训练时间约为10 s;当预测的切削状态数量为150时,预测时间仅为0.002s。在保证计算精度的前提下,三层神经网络模型可大幅提高计算效率。

Parameter uncertainty modeling of safety instrumented systems

In this study,a novel safety integrity level(SIL)determination methodology of safety instrumented systems(SISs)with parameter uncertainty is proposed by combining multistage dynamic Bayesian networks(DBNs)and Monte Carlo simulation.A multistage DBN model for SIL determination with multiple redundant cells is established.The models of function inspection test interval and function inspection test stages are alternately connected to form the multistage DBNs.The redundant cells can have different M out of N voting system architectures.An automatic modeling of conditional probability between nodes is developed.The SIL determination of SISs with parameter uncertainty is constructed by using the multistage DBNs and Monte Carlo simulation.A high-pressure SIS in the export of oil wellplatform is adopted to demonstrate the application of the proposed approach.The SIL and availability of the SIS and its subsystems are obtained.The influence of single subsystem on the SIL and availability of the SIS is studied.The influence of single redundant element on the SIL and availability of the subsystem is analyzed.A user-friendly SIL determination software with parameter uncertainty is developed on MATLAB graphical user interface.

基于混沌粒子群算法的机器人动力学参数辨识

文中提出了一种改进的混沌粒子群算法以优化机器人的激励轨迹,提高动力学参数辨识精度。首先,构建简化的SCARA机器人的动力学模型,选用改进的傅里叶级数作为激励轨迹并建立其优化目标和约束条件的数学模型;其次,在粒子群算法中引入动态控制参数策略和混沌搜索增强机制以优化调整算法参数和早熟粒子;最后,评估改进算法的寻优效果并利用其优化机器人的激励轨迹,进行基于神经网络的动力学参数辨识。仿真结果表明,所求的激励轨迹曲线平滑,机器人动力学参数辨识精度较高。

Effective prediction of DEA model by neural network

In this paper,a fast neural network model for the forecasting of effective points by DEA model is proposed,which is based on the SPDS training algorithm.The SPDS training algorithm overcomes the drawbacks of slow convergent speed and partially minimum result for BP algorithm.Its training speed is much faster and its forecasting precision is much better than those of BP algorithm.By numeric examples,it is showed that adopting the neural network model in the forecasting of effective points by DEA model is valid.

基于能量最小原则的高铁填料压实过程振动参数优化

为了动态优化高铁路基碾压参数,以提高高铁路基填料碾压效率,提出了一种基于振动能量最小原则的振动参数优化方法。首先,开展室内振动压实试验,以建立振动参数与干密度之间的定量关系;其次,采用改进神经网络方法建立干密度增量预测模型,构建基于能量最小原则的压实过程振动参数优化方法;最后,基于Modbus通讯协议,优化设计出振动参数可调的智能振动压实仪,并通过振动压实试验验证优化结果。研究结果表明:振动强度达到阈值后,进一步增大振动强度会导致压实仪发生“跳振”,严重影响振动设备使用寿命;改进神经网络模型能够较好用于预测干密度增量;提出适用于动态优化的遗算法(genetic algorithm,GA)算法的最佳参数,即种群数量为150,选择概率为0.9,交叉概率为0.6,变异概率为0.05;在此最佳参数下,能有效保证动态优化方法的准确性;采用优化后振动压实方案能够减少振动能量127.58 J,占优化前能量输出的25.61%,填料破碎率减小0.9%。

改进遗传-狼群对节点序寻优的贝叶斯网络结构算法

贝叶斯网络是数据挖掘领域的一种重要方法。针对贝叶斯网络结构学习算法寻优效率低和易陷入局部最优的问题,提出一种基于改进的混合遗传-狼群对节点序寻优的贝叶斯网络结构学习算法。该算法首先利用深度优先搜索对最大支撑树的节点进行拓扑排序;然后利用动态变异及最优交叉算子构建适用于节点序寻优的改进捕食行为,引入动态参数因子来增强算法局部寻优能力;最后与K2算法结合得到最优的贝叶斯网络结构。用3种不同大小的标准网络数据集中进行实验,结果表明,该算法收敛到较优值,寻优效率高于其它同类优化算法。