Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

In this paper, a filtering method is presented to estimate time-varying parameters of a missile dual control system with tail fins and reaction jets as control variables. In this method, the long-short-term memory(LSTM) neural network is nested into the extended Kalman filter(EKF) to modify the Kalman gain such that the filtering performance is improved in the presence of large model uncertainties. To avoid the unstable network output caused by the abrupt changes of system states,an adaptive correction factor is introduced to correct the network output online. In the process of training the network, a multi-gradient descent learning mode is proposed to better fit the internal state of the system, and a rolling training is used to implement an online prediction logic. Based on the Lyapunov second method, we discuss the stability of the system, the result shows that when the training error of neural network is sufficiently small, the system is asymptotically stable. With its application to the estimation of time-varying parameters of a missile dual control system, the LSTM-EKF shows better filtering performance than the EKF and adaptive EKF(AEKF) when there exist large uncertainties in the system model.

State estimation for neural neutral-type networks with mixed time-varying delays and Markovian jumping parameters

This paper is concerned with a delay-dependent state estimator for neutral-type neural networks with mixed timevarying delays and Markovian jumping parameters.The addressed neural networks have a finite number of modes,and the modes may jump from one to another according to a Markov process.By construction of a suitable Lyapunov-Krasovskii functional,a delay-dependent condition is developed to estimate the neuron states through available output measurements such that the estimation error system is globally asymptotically stable in a mean square.The criterion is formulated in terms of a set of linear matrix inequalities（LMIs）,which can be checked efficiently by use of some standard numerical packages.

Parameter estimation of continuous variable quantum key distribution system via artificial neural networks

Continuous-variable quantum key distribution(CVQKD)allows legitimate parties to extract and exchange secret keys.However,the tradeoff between the secret key rate and the accuracy of parameter estimation still around the present CVQKD system.In this paper,we suggest an approach for parameter estimation of the CVQKD system via artificial neural networks(ANN),which can be merged in post-processing with less additional devices.The ANN-based training scheme,enables key prediction without exposing any raw key.Experimental results show that the error between the predicted values and the true ones is in a reasonable range.The CVQKD system can be improved in terms of the secret key rate and the parameter estimation,which involves less additional devices than the traditional CVQKD system.

Resampling Factor Estimation via Dual-Stream Convolutional Neural Network

The estimation of image resampling factors is an important problem in image forensics.Among all the resampling factor estimation methods,spectrumbased methods are one of the most widely used methods and have attracted a lot of research interest.However,because of inherent ambiguity,spectrum-based methods fail to discriminate upscale and downscale operations without any prior information.In general,the application of resampling leaves detectable traces in both spatial domain and frequency domain of a resampled image.Firstly,the resampling process will introduce correlations between neighboring pixels.In this case,a set of periodic pixels that are correlated to their neighbors can be found in a resampled image.Secondly,the resampled image has distinct and strong peaks on spectrum while the spectrum of original image has no clear peaks.Hence,in this paper,we propose a dual-stream convolutional neural network for image resampling factors estimation.One of the two streams is gray stream whose purpose is to extract resampling traces features directly from the rescaled images.The other is frequency stream that discovers the differences of spectrum between rescaled and original images.The features from two streams are then fused to construct a feature representation including the resampling traces left in spatial and frequency domain,which is later fed into softmax layer for resampling factor estimation.Experimental results show that the proposed method is effective on resampling factor estimation and outperforms some CNN-based methods.

State-of-Charge Estimation of Lithium-Ion Battery for Electric Vehicles Using Deep Neural Network

It is critical to have precise data about Lithium-ion batteries,such as the State-of-Charge(SoC),to maintain a safe and consistent functioning of battery packs in energy storage systems of electric vehicles.Numerous strategies for estimating battery SoC,such as by including the coulomb counting and Kalman filter,have been established.As a result of the differences in parameter values between each cell,when these methods are applied to highcapacity battery packs,it has difficulties sustaining the prediction accuracy of overall cells.As a result of aging,the variation in the parameters of each cell is higher as more time is spent in operation.It is suggested in this study to establish an SoC estimate model for a Lithium-ion battery by employing an enhanced Deep Neural Network(DNN)approach.This is because the proposed DNN has a substantial hidden layer,which can accurately predict the SoC of an unknown driving cycle during training,making it ideal for SoC estimation.To evaluate the nonlinearities between voltage and current at various SoCs and temperatures,the proposed DNN is applied.Using current and voltage data measured at various temperatures throughout discharge/charge cycles is necessary for training and testing purposes.When the method has been thoroughly trained with the data collected,it is used for additional cells cycle tests to predict their SoC.The simulation has been conducted for two different Li-ion battery datasets.According to the experimental data,the suggested DNN-based SoC estimate approach produces a low mean absolute error and root-mean-square-error values,say less than 5%errors.

Parameters Estimation of an Electric Fan Using ANN

Electric Fans are very commonly used in the industries, domestic applications and in tunnels for cooling and ventila-tion purposes. Fan parameters estimation is an important task as far as the reliable operation of a fan system is con-cerned. Basically, a fan is mainly consisting of a single phase induction motor and therefore fan system parameters are essentially the electrical parameters e.g. resistances, reactances and some load parameters (fan blades).These parame-ters often change under varying operating conditions and the knowledge of these parameters is necessary to have opti-mum and efficient operation of the system. Therefore, fan system parameters are required to be estimated. Further, fan system parameters estimation is required to ensure the smooth system operation and to avoid any malfunctioning of the system during abnormal working conditions. In this paper, Artificial Neural Networks (ANN) approach has been used for parameter estimation of a fan system. The simulated and experimental results are compared.

A Novel Evolutionary Feedforward Neural Network with Artificial Immunology

A hybrid algorithm to design the multi layer feedforward neural network was proposed. Evolutionary programming is used to design the network that makes the training process tending to global optima. Artificial immunology combined with simulated annealing algorithm is used to specify the initial weight vectors, therefore improves the probabiligy of training algorithm to converge to global optima. The applications of the neural network in the modulation style recognition of analog modulated rader signals demonstrate the good performance of the network.

Evolution Performance of Symbolic Radial Basis Function Neural Network by Using Evolutionary Algorithms

Radial Basis Function Neural Network(RBFNN)ensembles have long suffered from non-efficient training,where incorrect parameter settings can be computationally disastrous.This paper examines different evolutionary algorithms for training the Symbolic Radial Basis Function Neural Network(SRBFNN)through the behavior’s integration of satisfiability programming.Inspired by evolutionary algorithms,which can iteratively find the nearoptimal solution,different Evolutionary Algorithms(EAs)were designed to optimize the producer output weight of the SRBFNN that corresponds to the embedded logic programming 2Satisfiability representation(SRBFNN-2SAT).The SRBFNN’s objective function that corresponds to Satisfiability logic programming can be minimized by different algorithms,including Genetic Algorithm(GA),Evolution Strategy Algorithm(ES),Differential Evolution Algorithm(DE),and Evolutionary Programming Algorithm(EP).Each of these methods is presented in the steps in the flowchart form which can be used for its straightforward implementation in any programming language.With the use of SRBFNN-2SAT,a training method based on these algorithms has been presented,then training has been compared among algorithms,which were applied in Microsoft Visual C++software using multiple metrics of performance,including Mean Absolute Relative Error(MARE),Root Mean Square Error(RMSE),Mean Absolute Percentage Error(MAPE),Mean Bias Error(MBE),Systematic Error(SD),Schwarz Bayesian Criterion(SBC),and Central Process Unit time(CPU time).Based on the results,the EP algorithm achieved a higher training rate and simple structure compared with the rest of the algorithms.It has been confirmed that the EP algorithm is quite effective in training and obtaining the best output weight,accompanied by the slightest iteration error,which minimizes the objective function of SRBFNN-2SAT.

Applying deep neural networks to the detection and space parameter estimation of compact binary coalescence with a network of gravitational wave detectors

In this paper, we study an application of deep learning to the advanced laser interferometer gravitational wave observatory(LIGO)and advanced Virgo coincident detection of gravitational waves(GWs) from compact binary star mergers. This deep learning method is an extension of the Deep Filtering method used by George and Huerta(2017) for multi-inputs of network detectors.Simulated coincident time series data sets in advanced LIGO and advanced Virgo detectors are analyzed for estimating source luminosity distance and sky location. As a classifier, our deep neural network(DNN) can effectively recognize the presence of GW signals when the optimal signal-to-noise ratio(SNR) of network detectors ≥ 9. As a predictor, it can also effectively estimate the corresponding source space parameters, including the luminosity distance D, right ascension α, and declination δ of the compact binary star mergers. When the SNR of the network detectors is greater than 8, their relative errors are all less than 23%.Our results demonstrate that Deep Filtering can process coincident GW time series inputs and perform effective classification and multiple space parameter estimation. Furthermore, we compare the results obtained from one, two, and three network detectors;these results reveal that a larger number of network detectors results in a better source location.

Finite-time robust control of uncertain fractional-order Hopfield neural networks via sliding mode control

The finite-time control of uncertain fractional-order Hopfield neural networks is investigated in this paper. A switched terminal sliding surface is proposed for a class of uncertain fractional-order Hopfield neural networks. Then a robust control law is designed to ensure the occurrence of the sliding motion for stabilization of the fractional-order Hopfield neural networks. Besides, for the unknown parameters of the fractional-order Hopfield neural networks, some estimations are made. Based on the fractional-order Lyapunov theory, the finite-time stability of the sliding surface to origin is proved well. Finally, a typical example of three-dimensional uncertain fractional-order Hopfield neural networks is employed to demonstrate the validity of the proposed method.

Parametric modeling of carbon nanotubes and estimating nonlocal constant using simulated vibration signals-ARMA and ANN based approach

Nonlocal continuum mechanics is a popular growing theory for investigating the dynamic behavior of Carbon nanotubes(CNTs).Estimating the nonlocal constant is a crucial step in mathematical modeling of CNTs vibration behavior based on this theory.Accordingly,in this study a vibration-based nonlocal parameter estimation technique,which can be competitive because of its lower instrumentation and data analysis costs,is proposed.To this end,the nonlocal models of the CNT by using the linear and nonlinear theories are established.Then,time response of the CNT to impulsive force is derived by solving the governing equations numerically.By using these time responses the parametric model of the CNT is constructed via the autoregressive moving average(ARMA)method.The appropriate ARMA parameters,which are chosen by an introduced feature reduction technique,are considered features to identify the value of the nonlocal constant.In this regard,a multi-layer perceptron(MLP)network has been trained to construct the complex relation between the ARMA parameters and the nonlocal constant.After training the MLP,based on the assumed linear and nonlinear models,the ability of the proposed method is evaluated and it is shown that the nonlocal parameter can be estimated with high accuracy in the presence/absence of nonlinearity.

Analytical Verification of Performance of Deep Neural Network Based Time-synchronized Distribution System State Estimation

Recently,we demonstrated the success of a time-synchronized state estimator using deep neural networks(DNNs)for real-time unobservable distribution systems.In this paper,we provide analytical bounds on the performance of the state estimator as a function of perturbations in the input measurements.It has already been shown that evaluating performance based only on the test dataset might not effectively indicate the ability of a trained DNN to handle input perturbations.As such,we analytically verify the robustness and trustworthiness of DNNs to input perturbations by treating them as mixed-integer linear programming(MILP)problems.The ability of batch normalization in addressing the scalability limitations of the MILP formulation is also highlighted.The framework is validated by performing time-synchronized distribution system state estimation for a modified IEEE 34-node system and a real-world large distribution system,both of which are incompletely observed by micro-phasor measurement units.

Aerodynamic Modeling and Parameter Estimation from QAR Data of an Airplane Approaching a High-altitude Airport

Aerodynamic modeling and parameter estimation from quick accesses recorder （QAR） data is an important technical way to analyze the effects of highland weather conditions upon aerodynamic characteristics of airplane. It is also an essential content of flight accident analysis. The related techniques are developed in the present paper, including the geometric method for angle of attack and sideslip angle estimation, the extended Kalman filter associated with modified Bryson-Frazier smoother （EKF-MBF） method for aerodynamic coefficient identification, the radial basis function （RBF） neural network method for aerodynamic mod- eling, and the Delta method for stability/control derivative estimation. As an application example, the QAR data of a civil air- plane approaching a high-altitude airport are processed and the aerodynamic coefficient and derivative estimates are obtained. The estimation results are reasonable, which shows that the developed techniques are feasible. The causes for the distribution of aerodynamic derivative estimates are analyzed. Accordingly, several measures to improve estimation accuracy are put forward.

Modelling reference evapotranspiration using gene expression programming and artificial neural network at Pantnagar,India

Evapotranspiration is an essential component of the hydrological cycle that is of particular interest for water resource planning.Its quantification is helpful in irrigation scheduling,water balance studies,water allocation,etc.Modelling of reference evapotranspiration(ET0)using both gene expression programming(GEP)and artificial neural network(ANN)techniques was done using the daily meteorological data of the Pantnagar region,India,from 2010 to 2019.A total of 15 combinations of inputs were used in developing the ET0 models.The model with the least number of inputs consisted of maximum and minimum air temperatures,whereas the model with the highest number of inputs consisted of maximum air temperature,minimum air temperature,mean relative humidity,number of sunshine hours,wind speed at 2mheight and extra-terrestrial radiation as inputs and with ET0 as the output for all the models.All the GEP models were developed for a single functional set and pre-defined genetic operator values,while the best structure in each ANN model was found based on the performance during the testing phase.It was found that ANN models were superior to GEP models for the estimation purpose.It was evident from the reduction in RMSE values ranging from 2%to 56%during training and testing phases in all the ANN models compared with GEP models.The ANN models showed an increase of about 0.96%to 9.72%of R2 value compared to the respective GEP models.The comparative study of these models with multiple linear regression(MLR)depicted that the ANN and GEP models were superior to MLR models.

Important Factors for Construction Project Cost Estimating Using ANN

Cost estimation has its proven importance as one of essential factors for project success. The aim of this research is to predict the early project cost using neural network. Early project cost represents a key component in business unit decisions. The most important factors influencing on the parametric cost estimation in construction building projects in Gaza Strip were defined and investigated. A questionnaire survey and relative index ranking technique were used to conclude the most important factors. Fourteen most effective factors were identified. One hundred and six case studies from real executed construction project in Gaza Strip were collected for training and testing the model. The cases were prepared to be used in cost estimate neural networks model. Eighty percent of case studies were used to train and test the model. The remaining 20% was used for model verification. The results revealed the ability to the model to predict cost estimate to an acceptable degree of accuracy. The minimum squares error with 0.005 in training stage and 0.021 in testing stage were recorded.

基于遥感多参数和CNN-Transformer的冬小麦单产估测

为了提高冬小麦单产估测精度,改善估产模型存在的高产低估和低产高估等现象,以陕西省关中平原为研究区域,选取旬尺度条件植被温度指数(VTCI)、叶面积指数(LAI)和光合有效辐射吸收比率(FPAR)为遥感特征参数,结合卷积神经网络(CNN)局部特征提取能力和基于自注意力机制的Transformer网络的全局信息提取能力,构建CNN-Transformer深度学习模型,用于估测关中平原冬小麦产量。与Transformer模型(R^(2)为0.64,RMSE为465.40 kg/hm^(2),MAPE为8.04%)相比,CNN-Transformer模型具有更高的冬小麦单产估测精度(R^(2)为0.70,RMSE为420.39 kg/hm^(2),MAPE为7.65%),能够从遥感多参数中提取更多与产量相关的信息,且对于Transformer模型存在的高产低估和低产高估现象均有所改善。基于5折交叉验证法和留一法进一步验证了CNN-Transformer模型的鲁棒性和泛化能力。此外,基于CNN-Transformer模型捕获冬小麦生长过程的累积效应,分析逐步累积旬尺度输入参数对产量估测的影响,评估模型对于冬小麦不同生长阶段的累积过程的表征能力。结果表明,模型能有效捕捉冬小麦生长的关键时期,3月下旬至5月上旬是冬小麦生长的关键时期。

基于卷积神经网络的预警震级分段估算方法

针对地震预警震级估算问题,提出一种基于卷积神经网络(convolutional neural network,CNN)的震级分段估算方法,该方法以单台站的P波初至后3 s时间的波形作为输入,输出结果为地震波形所属的震级区段(大地震,近震震级M_(L)≥5.0;小地震,M_(L)<5.0).如果波形属于大地震区段,直接发出警报;如果波形属于小地震区段,再进行具体震级的估算.对于震级区段估算,CNN模型的准确率可达98.04%.根据震级估算参数τ_(c)和P_(d)估算的小地震震级平均绝对误差(mean absolute error,MAE)分别为0.20和0.31.结果表明,预警震级分段估算方法可以准确预警大地震,减少大地震漏报率;同时使得小地震震级估算结果更为准确.

基于遥感多参数和IPSO-WNN的冬小麦单产估测

冬小麦是我国的主要粮食作物之一。为进一步准确地估测冬小麦产量,以陕西省关中平原为研究区域,选取冬小麦主要生育期与水分胁迫和光合作用等密切相关的条件植被温度指数(VTCI)、叶面积指数(LAI)和光合有效辐射吸收比率(FPAR)作为遥感特征参数,采用改进的粒子群算法优化小波神经网络(IPSO-WNN)以改善梯度下降方法易陷入局部最优的缺陷,并构建冬小麦产量估测模型。结果表明,IPSO-WNN模型的决定系数R2为0.66,平均绝对百分比误差(MAPE)为7.59%,相比于BPNN(R2=0.46,MAPE为11.80%)与WNN(R2=0.52,MAPE为9.80%),IPSO-WNN能够进一步提高模型的精度、增强模型的鲁棒性。采用灵敏度分析的方法探究对冬小麦产量影响较大的输入参数,结果发现,抽穗-灌浆期的FPAR对冬小麦产量影响最大,其次拔节期的VTCI、抽穗-灌浆期和乳熟期的LAI以及返青期和拔节期的FPAR对冬小麦产量的影响较大。通过IPSO-WNN输出获取冬小麦综合监测指数I,构建I与统计单产之间的估产模型以估测关中平原冬小麦单产,结果显示,估测单产与统计单产之间的R2为0.63,均方根误差(RMSE)为505.50 kg/hm^(2),相比于前人的研究较好地解决了估产模型存在的“低产高估”的问题,因此,本文基于IPSO-WNN构建的估产模型能够较准确地估测关中平原冬小麦产量。

基于编码矩阵估计的极化码参数盲识别算法

针对当前极化码参数识别算法缺少对码字起点的识别以及识别信息位算法计算复杂的问题,提出一种基于编码矩阵估计的极化码参数盲识别算法。所提算法首先将截获的码字矩阵、相应码长下的克罗内克矩阵以及逆向重排矩阵相乘得到编码矩阵估计,然后通过编码矩阵的分布特征识别出码长和码字起点,最后使用训练好的卷积神经网络对极化码信息位以及冻结位进行识别。实验结果表明,所提方法不仅完成了码字起点的识别,而且在未知码字起点的情况下完成了对码长的识别,且码长的识别准确率优于现有算法,误比特率在0.19时,参数为(32,12)的极化码码长识别率仍然可以达到90%以上。

基于LPNN的无源ML-TDOA估计

针对无源时差定位(TDOA)领域的非线性方程求解问题,提出了一种基于最大似然估计的改进型拉格朗日规划神经网络迭代求解算法。该算法利用最大似然估计构建代价函数,结合时空约束条件,建立TDOA方程的一般约束优化问题,并通过迭代求解算法对网络的收敛性和渐近稳定性进行了证明。针对两种常见的阵列排布方式进行了仿真验证与性能分析。仿真实验结果表明,该算法能够提供精确的坐标估计,误差小于1.414×10^(-3)。与传统算法相比,该方法在各类噪声环境下表现出更优的性能,尤其在0 dB噪声环境下,其均方误差为0.7866。