Approximation Property of the Modified Elman Network

A new type of recurrent neural network is discussed, which provides the potential for modelling unknown nonlinear systems. The proposed network is a generalization of the network described by Elman, which has three layers including the input layer, the hidden layer and the output layer. The input layer is composed of two different groups of neurons, the group of external input neurons and the group of the internal context neurons. Since arbitrary connections can be allowed from the hidden layer to the context layer, the modified Elman network has more memory space to represent dynamic systems than the Elman network. In addition, it is proved that the proposed network with appropriate neurons in the context layer can approximate the trajectory of a given dynamical system for any fixed finite length of time. The dynamic backpropagation algorithm is used to estimate the weights of both the feedforward and feedback connections. The methods have been successfully applied to the modelling of nonlinear plants.

Intelligent Fault Diagnosis for Planetary Gearbox Using Transferable Deep Q Network Under Variable Conditions with Small Training Data

Effective fault diagnosis of planetary gearboxes is critical for ensuring the safety and dependability of mechanical drive systems.Nevertheless,variable conditions and inadequate fault data bring huge challenges to its practical fault diagnosis.Taking this into account,this study presents a new intelligent fault diagnosis(IFD)approach for planetary gearbox using a transferable deep Q network(TDQN)that merges deep reinforcement learning(DRL)and transfer learning(TL).First,a DRL environment simulation is designed by a predefined classification Markov decision process.Then,leveraging varied-size convolutions and residual learning,a multiscale residual convolutional neural network agent for TDQN is created to automatically learn meaningful features directly from vibration signals while avoiding model degradation.Next,a large source dataset is obtained from complex conditions,and this agent learns an IFD policy via autonomous interaction with the data environment.Finally,a parameter-based TL strategy is adopted to retrain the model on target datasets with variable conditions and small training data,which is conducted by fine-tuning the model parameters gained from the source task to accomplish target tasks.The results show that this TDQN outperforms not only state-of-the-art methods in a source task with an accuracy of 98.53%but also in two target tasks with 99.63%and 98.37%,respectively.

Convergence of gradient method for Elman networks

The gradient method for training Elman networks with a finite training sample set is considered. Monotonicity of the error function in the iteration is shown. Weak and strong convergence results are proved, indicating that the gradient of the error function goes to zero and the weight sequence goes to a fixed point, respectively. A numerical example is given to support the theoretical findings.

NONLINEAR STABLE ADAPTIVE CONTROL BASED UPON ELMAN NETWORKS

Elman networks' dynamical modeling capability is discussed in this paper firstly.According to Elman networks' unique structure,a weight training algorithm is designed and a nonlinear adaptive controller is constructed.Without the PE presumption,neural networks controller's closed loop properties are studied and the whole Elman networks' passivity is demonstrated.

Parallel and optimized genetic Elman network for ^(252)Cf source-driven verification system

The 252Cf source-driven verification system(SDVS)can recognize the enrichment of fissile material with the enrichment-sensitive autocorrelation functions of a detector signal in252Cf source-driven noise-analysis(SDNA)measurements.We propose a parallel and optimized genetic Elman network(POGEN)to identify the enrichment of235U based on the physical properties of the measured autocorrelation functions.Theoretical analysis and experimental results indicate that,for 4 different enrichment fissile materials,due to higher information utilization,more efficient network architecture,and optimized parameters,the POGEN-based algorithm can obtain identification results with higher recognition accuracy,compared to the integrated autocorrelation function(IAF)method.

Prediction Model of Wax Deposition Rate in Waxy Crude Oil Pipelines by Elman Neural Network Based on Improved Reptile Search Algorithm

A hard problem that hinders the movement of waxy crude oil is wax deposition in oil pipelines.To ensure the safe operation of crude oil pipelines,an accurate model must be developed to predict the rate of wax deposition in crude oil pipelines.Aiming at the shortcomings of the ENN prediction model,which easily falls into the local minimum value and weak generalization ability in the implementation process,an optimized ENN prediction model based on the IRSA is proposed.The validity of the new model was confirmed by the accurate prediction of two sets of experimental data on wax deposition in crude oil pipelines.The two groups of crude oil wax deposition rate case prediction results showed that the average absolute percentage errors of IRSA-ENN prediction models is 0.5476% and 0.7831%,respectively.Additionally,it shows a higher prediction accuracy compared to the ENN prediction model.In fact,the new model established by using the IRSA to optimize ENN can optimize the initial weights and thresholds in the prediction process,which can overcome the shortcomings of the ENN prediction model,such as weak generalization ability and tendency to fall into the local minimum value,so that it has the advantages of strong implementation and high prediction accuracy.

Study on Ecological Change Remote Sensing Monitoring Method Based on Elman Dynamic Recurrent Neural Network

In this paper, Hailin City of Heilongjiang Province, China is taken as the research area. As an important city in Heilongjiang Province, China, the sustainable development of its ecological environment is related to the opening up, economic prosperity and social stability of Northeast China. In this paper, the remote sensing ecological index (RSEI) of Hailin City in recent 20 years was calculated by using Landsat 5/8/9 series satellite images, and the temporal and spatial changes of the ecological environment in Hailin City were further analyzed and the influencing factors were discussed. From 2003 to 2023, the mean value of RSEI in Hailin City decreased and increased, and the ecological environment decreased slightly as a whole. RSEI declined most significantly from 2003 to 2008, and it increased from 2008 to 2013, decreased from 2013 to 2018, and increased from 2018 to 2023 again, with higher RSEI value in the south and lower RSEI value in the northwest. It is suggested to appropriately increase vegetation coverage in the northwest to improve ecological quality. As a result, the predicted value of Elman dynamic recurrent neural network model is consistent with the change trend of the mean value, and the prediction error converges quickly, which can accurately predict the ecological environment quality in the future study area.

A dynamic-model-based fault diagnosis method for a wind turbine planetary gearbox using a deep learning network

The planetary gearbox is a critical part of wind turbines,and has great significance for their safety and reliability.Intelligent fault diagnosis methods for these gearboxes have made some achievements based on the availability of large quantities of labeled data.However,the data collected from the diagnosed devices are always unlabeled,and the acquisition of fault data from real gearboxes is time-consuming and laborious.As some gearbox faults can be conveniently simulated by a relatively precise dynamic model,the data from dynamic simulation containing some features are related to those from the actual machines.As a potential tool,transfer learning adapts a network trained in a source domain to its application in a target domain.Therefore,a novel fault diagnosis method combining transfer learning with dynamic model is proposed to identify the health conditions of planetary gearboxes.In the method,a modified lumped-parameter dynamic model of a planetary gear train is established to simulate the resultant vibration signal,while an optimized deep transfer learning network based on a one-dimensional convolutional neural network is built to extract domain-invariant features from different domains to achieve fault classification.Various groups of transfer diagnosis experiments of planetary gearboxes are carried out,and the experimental results demonstrate the effectiveness and the reliability of both the dynamic model and the proposed method.

Application Research of Temperature Forecasts on Elman Neural Network

[Objective] The aim was to establish Elman neural network model to predict the dynamic changes of temperature. [Method] Considering the inherent nature of temperature, and dy dint of the temperature in Chongqing during 1951-2010, the Elman artificial neural network model was applied to predict the temperature. [Result] This simulation result suggested that the relative error was small and can have a good simulation to the future temperature changes. [Conclusion] The prediction result can guide agricultural production and further apply to the field of pricing the weather derivative products.

基于IWOA-SA-Elman神经网络的短期风电功率预测

由于风力发电的随机性和不确定性使其短期功率的预测工作十分困难,而神经网络模型依靠其强大的自学习能力在风电功率预测领域有着广泛的应用。但神经网络预测精度受初始权重影响较大,且易出现过拟合的问题。为此构建一种基于改进鲸鱼算法和模拟退火组合优化的Elman神经网络短期风电功率预测模型,模型首先利用改进鲸鱼算法结合模拟退火策略获得高质量神经网络初始权值,接着引入正则化损失函数防止其过拟合,最后以西班牙瓦伦西亚某风电场陆上短期风电功率为研究对象,将该算法与BP、LSTM、Elman、WOA-Elman、IWOA-Elman 5种神经网络算法进行算法性能测试对比,结果表明IWOA-SA-Elman神经网络模型预测误差最小,验证了该算法的合理性和有效性。

Wind Turbine Gearbox Fault Diagnosis Based on Multi-sensor Signals Fusion

This paper proposes a novel fault diagnosis method by fusing the information from multi-sensor signals to improve the reliability of the conventional vibration-based wind turbine drivetrain gearbox fault diagnosis methods.The method fully extracts fault features for variable speed,insufficient samples,and strong noise scenarios that may occur in the actual operation of a wind turbine planetary gearbox.First,multiple sensor signals are added to the diagnostic model,and multiple stacked denoising auto-encoders are designed and improved to extract the fault information.Then,a cycle reservoir with regular jumps is introduced to fuse multidimensional fault information and output diagnostic results in response to the insufficient ability to process fused information by the conventional Softmax classifier.In addition,the competitive swarm optimizer algorithm is introduced to address the challenge of obtaining the optimal combination of parameters in the network.Finally,the validation results show that the proposed method can increase fault diagnostic accuracy and improve robustness.

基于PSO-Elman神经网络的井底风温预测模型

目前井下风温预测大多采用BP神经网络,但其预测精度受学习样本数量的影响,且容易陷入局部最优,Elman神经网络具备局部记忆能力,提高了网络的稳定性和动态适应能力,但仍然存在收敛速度过慢、易陷入局部最优的问题。针对上述问题,采用粒子群优化(PSO)算法对Elman神经网络的权值和阈值进行优化,建立了基于PSO-Elman神经网络的井底风温预测模型。分析得出入风相对湿度、入风温度、地面大气压力和井筒深度是井底风温的主要影响因素,因此将其作为模型的输入数据,模型的输出数据为井底风温。在相同样本数据集下的实验结果表明:Elman模型迭代90次后收敛,PSO-Elman模型迭代41次后收敛,说明PSO-Elman模型收敛速度更快;与BP神经网络模型、支持向量回归模型和Elman模型相比,PSO-Elman模型的预测误差较低,平均绝对误差、均方误差(MSE)、平均绝对百分比误差分别为0.376 0℃,0.278 3,1.95%,决定系数R^(2)为0.992 4,非常接近1,表明预测模型具有良好的预测效果。实例验证结果表明,PSO-Elman模型的相对误差范围为-4.69%~1.27%,绝对误差范围为-1.06~0.29℃,MSE为0.26,整体预测精度可满足井下实际需要。

基于改进SFLA-Elman神经网络的电离层杂波抑制方法

针对高频地波雷达目标检测中电离层杂波的干扰问题,提出了一种基于改进混合蛙跳算法优化Elman神经网络预测抑制电离层杂波的策略。为解决混合蛙跳算法初始种群分布不均匀、收敛精度低、易陷于局部极值等问题,引入Cubic混沌映射、莱维飞行策略、非线性平衡因子和复制操作,增强种群多样性,提高算法搜索能力。利用改进后的算法和其他算法分别优化Elman神经网络预测抑制模型,结果表明,改进后的算法无论是在收敛精度和稳定性上,还是在临近距离单元电离层杂波的预测抑制上,都取得了显著的提升。在基本保留目标信号的基础上,平均信杂比较原始回波提升18.52 dB,较原始混合蛙跳算法提升1.08 dB,对于电离层杂波的抑制具有较高应用价值。

基于RSSR融合RNGO-Elman神经网络的室内可见光定位

针对动态环境下基于接收信号强度的传统可见光定位方法定位精度低、稳定性差等问题,提出一种基于接收信号强度比的改进北方苍鹰算法(NGO)优化Elman神经网络(RNGOElman)的室内可见光定位系统。提出选择一个辅助参考点,将待测参考点与辅助参考点的接收信号强度比值和接收机的真实位置作为训练集数据,建立不受动态环境影响的指纹数据库。针对NGO算法收敛速度慢、容易陷入局部最优等问题,利用折射反向学习策略初始化种群,增加种群多样性,引入非线性权重因子来加快收敛速度,避免陷入局部最优。使用优化后的NGO算法来优化Elman神经网络的初始权值和阈值,构建RNGO-Elman动态定位预测模型。仿真结果表明,在4m×4m×3m的实验空间下,优化后的RNGO-Elman定位模型平均定位误差为1.34cm,定位精度相较于Elman定位算法、NGO-Elman定位算法分别提高了82%,21%。在LED发射功率波动时,基于RSSR的RNGO-Elman定位误差为1.29cm,1.38cm。所提可见光定位方法具有定位精度高、定位性能稳定等优点。

A mixture of HMM,GA,and Elman network for load prediction in cloud-oriented data centers

The rapid growth of computational power demand from scientific,business,and Web applications has led to the emergence of cloud-oriented data centers.These centers use pay-as-you-go execution environments that scale transparently to the user.Load prediction is a significant cost-optimal resource allocation and energy saving approach for a cloud computing environment.Traditional linear or nonlinear prediction models that forecast future load directly from historical information appear less effective.Load classification before prediction is necessary to improve prediction accuracy.In this paper,a novel approach is proposed to forecast the future load for cloud-oriented data centers.First,a hidden Markov model(HMM) based data clustering method is adopted to classify the cloud load.The Bayesian information criterion and Akaike information criterion are employed to automatically determine the optimal HMM model size and cluster numbers.Trained HMMs are then used to identify the most appropriate cluster that possesses the maximum likelihood for current load.With the data from this cluster,a genetic algorithm optimized Elman network is used to forecast future load.Experimental results show that our algorithm outperforms other approaches reported in previous works.

FOUR-PARAMETER AUTOMATIC TRANSMISSION TECHNOLOGY FOR CONSTRUCTION VEHICLE BASED ON ELMAN RECURSIVE NEURAL NETWORK

From the viewpoint of energy saving and improving transmission efficiency, the ZL50E wheel loader is taken as the study object. And the system model is analyzed based on the transmission system of the construction vehicle. A new four-parameter shift schedule is presented, which can keep the torque converter working in the high efficiency area. The control algorithm based on the Elman recursive neural network is applied, and four-parameter control system is developed which is based on industrial computer. The system is used to collect data accurately and control 4D180 power-shift gearbox of ZL50E wheel loader shift timely. An experiment is done on automatic transmission test-bed, and the result indicates that the control system could reliably and safely work and improve the efficiency of hydraulic torque converter. Four-parameter shift strategy that takes into account the power consuming of the working pump has important operating significance and reflects the actual working status of construction vehicle.

基于IPSO-Elman的气液两相流含气率测量方法

为安全且非侵入式地测量气液两相流含气率,提出一种电阻层析成像(ERT)陈列电阻与Elman神经网络相结合的含气率测量方法。首先,为加快模型训练速度并避免数据冗余,使用主成分分析(PCA)算法对120维的阵列电阻特征降维。然后,在粒子群(PSO)算法中引入自适应惯性权重和非线性学习因子,并加入遗传算法(GA)的交叉和变异行为以加快算法收敛速度。最后,通过改进的粒子群(IPSO)算法优化Elman神经网络初始权值和阈值,并建立含气率测量模型。经对比实验发现,PCA-IPSO-Elman含气率测量模型的平均绝对百分比误差为2.92%,且训练时间较IPSO-Elman模型减少68.8%。说明所提方法可以达到预期的测量效果。

Actuator fault diagnosis of autonomous underwater vehicle based on improved Elman neural network

Autonomous underwater vehicles(AUV) work in a complex marine environment. Its system reliability and autonomous fault diagnosis are particularly important and can provide the basis for underwater vehicles to take corresponding security policy in a failure. Aiming at the characteristics of the underwater vehicle which has uncertain system and modeling difficulty, an improved Elman neural network is introduced which is applied to the underwater vehicle motion modeling. Through designing self-feedback connection with fixed gain in the unit connection as well as increasing the feedback of the output layer node, improved Elman network has faster convergence speed and generalization ability. This method for high-order nonlinear system has stronger identification ability. Firstly, the residual is calculated by comparing the output of the underwater vehicle model(estimation in the motion state) with the actual measured values. Secondly, characteristics of the residual are analyzed on the basis of fault judging criteria. Finally, actuator fault diagnosis of the autonomous underwater vehicle is carried out. The results of the simulation experiment show that the method is effective.

Multicomponent Kinetic Determination by Wavelet Packet Transform Based Elman Recurrent Neural Network Method

This paper covers a novel method named wavelet packet transform based Elman recurrent neural network(WPTERNN) for the simultaneous kinetic determination of periodate and iodate. The wavelet packet representations of signals provide a local time-frequency description, thus in the wavelet packet domain, the quality of the noise removal can be improved. The Elman recurrent network was applied to non-linear multivariate calibration. In this case, by means of optimization, the wavelet function, decomposition level and number of hidden nodes for WPTERNN method were selected as D4, 5 and 5 respectively. A program PWPTERNN was designed to perform multicomponent kinetic determination. The relative standard error of prediction(RSEP) for all the components with WPTERNN, Elman RNN and PLS were 3.23%, 11.8% and 10.9% respectively. The experimental results show that the method is better than the others.

Predication of plasma concentration of remifentanil based on Elman neural network

Due to the nature of ultra-short-acting opioid remifentanil of high time-varying,complex compartment model and low-accuracy of plasma concentration prediction,the traditional estimation method of population pharmacokinetics parameters,nonlinear mixed effects model(NONMEM),has the abuses of tedious work and plenty of man-made jamming factors.The Elman feedback neural network was built.The relationships between the patients’plasma concentration of remifentanil and time,patient’age,gender,lean body mass,height,body surface area,sampling time,total dose,and injection rate through network training were obtained to predict the plasma concentration of remifentanil,and after that,it was compared with the results of NONMEM algorithm.In conclusion,the average error of Elman network is 6.34%,while that of NONMEM is 18.99%.The absolute average error of Elman network is 27.07%,while that of NONMEM is 38.09%.The experimental results indicate that Elman neural network could predict the plasma concentration of remifentanil rapidly and stably,with high accuracy and low error.For the characteristics of simple principle and fast computing speed,this method is suitable to data analysis of short-acting anesthesia drug population pharmacokinetic and pharmacodynamics.