System Identification becomes very crucial in the field of nonlinear and dynamic systems or practical systems.As most practical systems don’t have prior information about the system behaviour thus,mathematical modell...System Identification becomes very crucial in the field of nonlinear and dynamic systems or practical systems.As most practical systems don’t have prior information about the system behaviour thus,mathematical modelling is required.The authors have proposed a stacked Bidirectional Long-Short Term Memory(Bi-LSTM)model to handle the problem of nonlinear dynamic system identification in this paper.The proposed model has the ability of faster learning and accurate modelling as it can be trained in both forward and backward directions.The main advantage of Bi-LSTM over other algorithms is that it processes inputs in two ways:one from the past to the future,and the other from the future to the past.In this proposed model a backward-running Long-Short Term Memory(LSTM)can store information from the future along with application of two hidden states together allows for storing information from the past and future at any moment in time.The proposed model is tested with a recorded speech signal to prove its superiority with the performance being evaluated through Mean Square Error(MSE)and Root Means Square Error(RMSE).The RMSE and MSE performances obtained by the proposed model are found to be 0.0218 and 0.0162 respectively for 500 Epochs.The comparison of results and further analysis illustrates that the proposed model achieves better performance over other models and can obtain higher prediction accuracy along with faster convergence speed.展开更多
Tool condition monitoring(TCM)is a key technology for intelligent manufacturing.The objective is to monitor the tool operation status and detect tool breakage so that the tool can be changed in time to avoid significa...Tool condition monitoring(TCM)is a key technology for intelligent manufacturing.The objective is to monitor the tool operation status and detect tool breakage so that the tool can be changed in time to avoid significant damage to workpieces and reduce manufacturing costs.Recently,an innovative TCM approach based on sensor data modelling and model frequency analysis has been proposed.Different from traditional signal feature-based monitoring,the data from sensors are utilized to build a dynamic process model.Then,the nonlinear output frequency response functions,a concept which extends the linear system frequency response function to the nonlinear case,over the frequency range of the tooth passing frequency of the machining process are extracted to reveal tool health conditions.In order to extend the novel sensor data modelling and model frequency analysis to unsupervised condition monitoring of cutting tools,in the present study,a multivariate control chart is proposed for TCM based on the frequency domain properties of machining processes derived from the innovative sensor data modelling and model frequency analysis.The feature dimension is reduced by principal component analysis first.Then the moving average strategy is exploited to generate monitoring variables and overcome the effects of noises.The milling experiments of titanium alloys are conducted to verify the effectiveness of the proposed approach in detecting excessive flank wear of solid carbide end mills.The results demonstrate the advantages of the new approach over conventional TCM techniques and its potential in industrial applications.展开更多
In this research, we present a methodology to identify the Hammerstein nonlinear system with noisy output measurements. The Hammerstein system presented is comprised of neural fuzzy model (NFM) as its static nonlinear...In this research, we present a methodology to identify the Hammerstein nonlinear system with noisy output measurements. The Hammerstein system presented is comprised of neural fuzzy model (NFM) as its static nonlinear block and auto-regressive with extra input (ARX) model as its dynamic linear block, and a two-step procedure is accomplished using signal combination. In the first step, in the case of input–output of Gaussian signals, the correlation function-based least squares (CF-LS) technique is utilized to identify the linear block, solving the problem that the intermediate variable connecting nonlinear and linear blocks cannot be measured. In the second step, to improve the identification accuracy of the nonlinear block parameters, an improved particle swarm optimization technique is developed under input–output of random signals. The validity and accuracy of the presented scheme are verified by a numerical simulation and a practical nonlinear process, and the results illustrate that the proposed methodology can identify well the Hammerstein nonlinear system with noisy output measurements.展开更多
通过一维杆的一维传热的分组显式数值求解,分析热弹性效应的存在及规律,得出随着时间的增长,温升—热变形之间的关系会逐渐趋近稳态,但不可能获得绝对的稳态;在传热过程中,随着距离增加,温度衰减很快,离热源越远的点的热弹性效环应越窄...通过一维杆的一维传热的分组显式数值求解,分析热弹性效应的存在及规律,得出随着时间的增长,温升—热变形之间的关系会逐渐趋近稳态,但不可能获得绝对的稳态;在传热过程中,随着距离增加,温度衰减很快,离热源越远的点的热弹性效环应越窄。提出用非线性时序模型与前向神经网络相结合的模型(Nonlinear auto-regressive moving average neural network with exogenousinputs,NARMAX-NN)来辨识热弹性效应。用NARMAX-NN模型对高速进给系统试验台的热动态特性进行建模,获得良好的效果。此方法比多变量回归模型、反馈神经网络模型及广义最小二乘输出误差模型有更好的精度和鲁棒性,能精确地对复杂结构、多热源的时变非线性热误差特性进行建模和预测。展开更多
提出了一种软件系统的非线性有源自回归(Nonlinear AutoRegressive models with eXogenous Inputs,NARX)网络模型的老化检测方法。解决了目前软件老化方法未考虑多变量间关联性及历史数据的延迟影响的问题。该方法首先通过对实验采集的H...提出了一种软件系统的非线性有源自回归(Nonlinear AutoRegressive models with eXogenous Inputs,NARX)网络模型的老化检测方法。解决了目前软件老化方法未考虑多变量间关联性及历史数据的延迟影响的问题。该方法首先通过对实验采集的HelixServer-VOD服务器性能数据进行主成分分析,确定网络的输入维数,根据AIC准则确定最佳模型阶数,最终选取合理的网络模型结构;使用已知的未老化状态样本对NARX网络进行训练,建立系统的辨识模型;然后运用序贯概率比检验(Sequential Probability Ratio Test,SPRT)对NARX辨识模型的残差进行假设检验,判断系统的老化状态。实验分析表明,基于NARX网络模型的故障检测方法能够有效地应用于软件老化的检测。展开更多
文摘System Identification becomes very crucial in the field of nonlinear and dynamic systems or practical systems.As most practical systems don’t have prior information about the system behaviour thus,mathematical modelling is required.The authors have proposed a stacked Bidirectional Long-Short Term Memory(Bi-LSTM)model to handle the problem of nonlinear dynamic system identification in this paper.The proposed model has the ability of faster learning and accurate modelling as it can be trained in both forward and backward directions.The main advantage of Bi-LSTM over other algorithms is that it processes inputs in two ways:one from the past to the future,and the other from the future to the past.In this proposed model a backward-running Long-Short Term Memory(LSTM)can store information from the future along with application of two hidden states together allows for storing information from the past and future at any moment in time.The proposed model is tested with a recorded speech signal to prove its superiority with the performance being evaluated through Mean Square Error(MSE)and Root Means Square Error(RMSE).The RMSE and MSE performances obtained by the proposed model are found to be 0.0218 and 0.0162 respectively for 500 Epochs.The comparison of results and further analysis illustrates that the proposed model achieves better performance over other models and can obtain higher prediction accuracy along with faster convergence speed.
文摘Tool condition monitoring(TCM)is a key technology for intelligent manufacturing.The objective is to monitor the tool operation status and detect tool breakage so that the tool can be changed in time to avoid significant damage to workpieces and reduce manufacturing costs.Recently,an innovative TCM approach based on sensor data modelling and model frequency analysis has been proposed.Different from traditional signal feature-based monitoring,the data from sensors are utilized to build a dynamic process model.Then,the nonlinear output frequency response functions,a concept which extends the linear system frequency response function to the nonlinear case,over the frequency range of the tooth passing frequency of the machining process are extracted to reveal tool health conditions.In order to extend the novel sensor data modelling and model frequency analysis to unsupervised condition monitoring of cutting tools,in the present study,a multivariate control chart is proposed for TCM based on the frequency domain properties of machining processes derived from the innovative sensor data modelling and model frequency analysis.The feature dimension is reduced by principal component analysis first.Then the moving average strategy is exploited to generate monitoring variables and overcome the effects of noises.The milling experiments of titanium alloys are conducted to verify the effectiveness of the proposed approach in detecting excessive flank wear of solid carbide end mills.The results demonstrate the advantages of the new approach over conventional TCM techniques and its potential in industrial applications.
基金supported by the National Natural Science Foundation of China(62003151)the Changzhou Science and Technology Bureau(CJ20220065,CM20223015)+1 种基金the Qinglan Project of Jiangsu Province of Chinathe Zhongwu Youth Innovative Talents Support Program in Jiangsu University of Technology.
文摘In this research, we present a methodology to identify the Hammerstein nonlinear system with noisy output measurements. The Hammerstein system presented is comprised of neural fuzzy model (NFM) as its static nonlinear block and auto-regressive with extra input (ARX) model as its dynamic linear block, and a two-step procedure is accomplished using signal combination. In the first step, in the case of input–output of Gaussian signals, the correlation function-based least squares (CF-LS) technique is utilized to identify the linear block, solving the problem that the intermediate variable connecting nonlinear and linear blocks cannot be measured. In the second step, to improve the identification accuracy of the nonlinear block parameters, an improved particle swarm optimization technique is developed under input–output of random signals. The validity and accuracy of the presented scheme are verified by a numerical simulation and a practical nonlinear process, and the results illustrate that the proposed methodology can identify well the Hammerstein nonlinear system with noisy output measurements.
基金This research is supported by the National Nature Science Foundation of China under Grant No.60574007the Nature Science Foundation of Shandong Province under Grant No.Y2003G02.
文摘通过一维杆的一维传热的分组显式数值求解,分析热弹性效应的存在及规律,得出随着时间的增长,温升—热变形之间的关系会逐渐趋近稳态,但不可能获得绝对的稳态;在传热过程中,随着距离增加,温度衰减很快,离热源越远的点的热弹性效环应越窄。提出用非线性时序模型与前向神经网络相结合的模型(Nonlinear auto-regressive moving average neural network with exogenousinputs,NARMAX-NN)来辨识热弹性效应。用NARMAX-NN模型对高速进给系统试验台的热动态特性进行建模,获得良好的效果。此方法比多变量回归模型、反馈神经网络模型及广义最小二乘输出误差模型有更好的精度和鲁棒性,能精确地对复杂结构、多热源的时变非线性热误差特性进行建模和预测。
文摘提出了一种软件系统的非线性有源自回归(Nonlinear AutoRegressive models with eXogenous Inputs,NARX)网络模型的老化检测方法。解决了目前软件老化方法未考虑多变量间关联性及历史数据的延迟影响的问题。该方法首先通过对实验采集的HelixServer-VOD服务器性能数据进行主成分分析,确定网络的输入维数,根据AIC准则确定最佳模型阶数,最终选取合理的网络模型结构;使用已知的未老化状态样本对NARX网络进行训练,建立系统的辨识模型;然后运用序贯概率比检验(Sequential Probability Ratio Test,SPRT)对NARX辨识模型的残差进行假设检验,判断系统的老化状态。实验分析表明,基于NARX网络模型的故障检测方法能够有效地应用于软件老化的检测。
文摘极限学习机(Extreme learning machine,ELM)是一种单隐层前馈神经网络(SLFNs),它随机选择网络的隐含层节点及其参数,训练时仅需调节输出层权值,因此ELM以极快的学习速度获得良好的推广性。考虑到ELM的特征映射函数未知时,可以将核矩阵引入到ELM中。针对模型未知的强非线性连续搅拌反应釜(Continuous Stirred Tank Reactor,CSTR),提出一种基于核极限学习机(Extreme Learning Machine with Kernels,KELM)的NARX模型辨识方法。以仿真的CSTR过程实例进行辨识实验,建立基于NARX-KELM的辨识模型。实验结果表明,在相同条件下,与带动量因子的BP神经网络、模糊神经网络(FNN)、GAP-RBF、MGAP-RBF神经网络、回声状态网络(ESN)、ELM等方法相比,KELM能够有效地改进辨识精度,而且性能更好,这表明了所提方法的有效性和应用潜力。
