A robust hybrid model integrating enhanced inputs based extreme learning machine with PLSR (PLSR-EIELM) and its application to intelligent measurement

In this paper, a robust hybrid model integrating an enhanced inputs based extreme learning machine with the partial least square regression (PLSR-EIELM) was proposed. The proposed PLSR-EIELM model can overcome two main flaws in the extreme learning machine (ELM), i.e. the intractable problem in determining the optimal number of the hidden layer neurons and the over-fitting phenomenon. First, a traditional extreme learning machine (ELM) is selected. Second, a method of randomly assigning is applied to the weights between the input layer and the hidden layer, and then the nonlinear transformation for independent variables can be obtained from the output of the hidden layer neurons. Especially, the original input variables are regarded as enhanced inputs; then the enhanced inputs and the nonlinear transformed variables are tied together as the whole independent variables. In this way, the PLSR can be carried out to identify the PLS components not only from the nonlinear transformed variables but also from the original input variables, which can remove the correlation among the whole independent variables and the expected outputs. Finally, the optimal relationship model of the whole independent variables with the expected outputs can be achieved by using PLSR. Thus, the PLSR-EIELM model is developed. Then the PLSR-EIELM model served as an intelligent measurement tool for the key variables of the Purified Terephthalic Acid (PTA) process and the High Density Polyethylene (HDPE) process. The experimental results show that the predictive accuracy of PLSR-EIELM is stable, which indicate that PLSR-EIELM has good robust character. Moreover, compared with ELM, PLSR, hierarchical ELM (HELM), and PLSR-ELM, PLSR-EIELM can achieve much smaller predicted relative errors in these two applications.     

A modified NARMAX model-based self-tuner with fault tolerance for unknown nonlinear stochastic hybrid systems with an input–output direct feed-through term

A modified nonlinear autoregressive moving average with exogenous inputs (NARMAX) model-based state-space self-tuner with fault tolerance is proposed in this paper for the unknown nonlinear stochastic hybrid system with a direct transmission matrix from input to output. Through the off-line observer/Kalman filter identification method, one has a good initial guess of modified NARMAX model to reduce the on-line system identification process time. Then, based on the modified NARMAX-based system identification, a corresponding adaptive digital control scheme is presented for the unknown continuous-time nonlinear system, with an input–output direct transmission term, which also has measurement and system noises and inaccessible system states. Besides, an effective state space self-turner with fault tolerance scheme is presented for the unknown multivariable stochastic system. A quantitative criterion is suggested by comparing the innovation process error estimated by the Kalman filter estimation algorithm, so that a weighting matrix resetting technique by adjusting and resetting the covariance matrices of parameter estimate obtained by the Kalman filter estimation algorithm is utilized to achieve the parameter estimation for faulty system recovery. Consequently, the proposed method can effectively cope with partially abrupt and/or gradual system faults and input failures by the fault detection.     

Hybrid modeling for robust nonlinear multivariable control

This paper describes a hybrid modeling approach and compares it to classic linear dynamic models and nonlinear models. Particular attention is given to the performance of each type of model when embedded in a multivariable model predictive control system. The hybrid approach combines linear state-space model with a nonlinear neural network correction. Confidence computations are used to determine the amount of correction applied. The combined model is adapted online to address changes in process operating range. The hybrid structure offers several benefits from a control perspective. It is evolutionary, building on the rich theoretical foundation of linear model predictive control. It can model nonlinear processes. It adapts online. When compared to other linear and nonlinear modeling techniques for control purposes, it has several specific advantages that make it ideally suited to particular applications. These applications include modeling and controlling: nonlinear processes, processes with slowly changing inputs, processes with interacting variables, and small systems with fast cycle time requirements.     

Tracking control of nonlinear lumped mechanical continuous-time systems: A model-based iterative learning approach

This paper presents a nonlinear model-based iterative learning control procedure to achieve accurate tracking control for nonlinear lumped mechanical continuous-time systems. The model structure used in this iterative learning control procedure is new and combines a linear state space model and a nonlinear feature space transformation. An intuitive two-step iterative algorithm to identify the model parameters is presented. It alternates between the estimation of the linear and the nonlinear model part. It is assumed that besides the input and output signals also the full state vector of the system is available for identification. A measurement and signal processing procedure to estimate these signals for lumped mechanical systems is presented. The iterative learning control procedure relies on the calculation of the input that generates a given model output, so-called offline model inversion. A new offline nonlinear model inversion method for continuous-time, nonlinear time-invariant, state space models based on Newton's method is presented and applied to the new model structure. This model inversion method is not restricted to minimum phase models. It requires only calculation of the first order derivatives of the state space model and is applicable to multivariable models. For periodic reference signals the method yields a compact implementation in the frequency domain. Moreover it is shown that a bandwidth can be specified up to which learning is allowed when using this inversion method in the iterative learning control procedure. Experimental results for a nonlinear single-input-single-output system corresponding to a quarter car on a hydraulic test rig are presented. It is shown that the new nonlinear approach outperforms the linear iterative learning control approach which is currently used in the automotive industry on durability test rigs.     

Adaptive extended state space predictive control for a kind of nonlinear systems

This paper presents an adaptive nonlinear predictive control design strategy for a kind of nonlinear systems with output feedback coupling and results in the improvement of regulatory capacity for reference tracking, robustness and disturbance rejection. The nonlinear system is first transformed into an equal time-variant system by analyzing the nonlinear part. Then an extended state space predictive controller with a similar structure of a PI optimal regulator and with P-step setpoint feedforward control is designed. Because changes of the system state variables are considered in the objective function, the control performance is superior to conventional state space predictive control designs which only consider the predicted output errors. The proposed method is tested and compared with latest methods in literature. Tracking performance, robustness and disturbance rejection are improved.     

Improved control using extended non-minimal state space MPC and modified LQR for a kind of nonlinear systems

Inspired by the state space model based predictive control, this paper presents the combination design of extended non-minimal state space predictive control (ENMSSPC) and modified linear quadratic regulator (LQR) for a kind of nonlinear process with output feedback coupling, which shows improved control performance for both model/plant match and model/plant mismatch cases. In many previous control methods for this kind of nonlinear systems, the nonlinear part is treated in different ways such as ignored, represented as a rough linear one or assumed to be time-variant when corresponding predictive control methods are designed. However, the above methods will generally lead to information loss, resulting in the influenced control performance. This paper will show that the ENMSSPC-LQ control structure will further improve closed-loop control performance concerning tracking ability and disturbance rejection compared with previous predictive control methods.     

A novel linear ridgelet network approach for analog fault diagnosis using wavelet-based fractal analysis and kernel PCA as preprocessors

We have developed a novel fault diagnosis approach of analog circuits based on linear ridgelet network using wavelet-based fractal analysis, kernel principal components analysis (kernel PCA) as preprocessors. The proposed approach can detect and identify faulty components in the analog circuits by analyzing their time responses. First, using wavelet-based fractal analysis to preprocess the time responses obtains the essential and reduced candidate features of the corresponding response signals. Then, the second preprocessing by kernel PCA further reduces the dimensionality of candidate features so as to obtain the optimal features as inputs to linear ridgelet networks. Meanwhile, we also adopt the kernel PCA to select the proper numbers of hidden ridgelet neurons of the linear ridgelet networks. The simulation results show that the resulting diagnostic system using these techniques can not only simplify the architectures (including input nodes and hidden neurons) and minimize the training and processing time of these networks considerably, but also diagnose single and multiple faults effectively in classifying faulty components of example circuits to improve the accuracy and efficiency of fault diagnosis with a highly correct classification rate.     

An improved artificial neural network for laser welding parameter selection and prediction

In the laser welding production, the selection and prediction of welding parameters is essentially important to guarantee weld quality. Artificial neural networks (ANN), which perform a nonlinear mapping between inputs and outputs, are an alternative approach for developing welding parameter forecasting model. In this paper, in order to speed up the convergence and avoid local minimum of the conditional ANN, genetic algorithm simulated annealing (GASA) based on the random global optimization is inducted into the network training. By means of GASA method, weights and threshold of neural networks can be globally optimized with short training time. Meanwhile, the gray correlation model (GCM) is used as a pre-processing tool to simplify the original networks based on obtaining the main influence elements of network inputs. The GCM–GASA–ANN method combines the complementary features of three computational intelligence techniques and owns very good applicability. Through the simulation and analysis of an orthogonal experiment, the proposed method can be proved to have higher accuracy and to perform better than the traditional ANN to forecast the laser welding parameters.     

Nonlinear predictive control of a boiler-turbine unit: A state-space approach with successive on-line model linearisation and quadratic optimisation

This paper details development of a Model Predictive Control (MPC) algorithm for a boiler-turbine unit, which is a nonlinear multiple-input multiple-output process. The control objective is to follow set-point changes imposed on two state (output) variables and to satisfy constraints imposed on three inputs and one output. In order to obtain a computationally efficient control scheme, the state-space model is successively linearised on-line for the current operating point and used for prediction. In consequence, the future control policy is easily calculated from a quadratic optimisation problem. For state estimation the extended Kalman filter is used. It is demonstrated that the MPC strategy based on constant linear models does not work satisfactorily for the boiler-turbine unit whereas the discussed algorithm with on-line successive model linearisation gives practically the same trajectories as the truly nonlinear MPC controller with nonlinear optimisation repeated at each sampling instant.     

Interpolating model identification for SISO linear parameter-varying systems

This paper presents a new method to estimate linear parameter-varying (LPV) state-space models for single-input single-output systems whose dynamics depend on one or more time-varying parameters, called scheduling parameters. The method is based on the interpolation of linear time-invariant models that are identified for fixed operating conditions of the system, that is, for constant values of the scheduling parameters. The proposed method can account for multiple scheduling parameters and yields either a polynomial or an affine LPV model that is numerically well-conditioned and therefore suitable for LPV control synthesis. The underlying interpolation technique is formulated as a nonlinear least-squares optimization problem that can be solved efficiently by standard solvers. The new interpolation method is applied to an electromechanical system that depends on two scheduling parameters. The numerical results are compared to existing techniques in the literature, demonstrating the potential and advantages of the proposed method.     

基于BP网络的水轮机修复专用机器人运动学逆解分析

用Pro-E软件建立了水轮机修复专用机器人的本体模型，在此基础上，利用Matlab循环程序求出机器人在给定关节变量下的运动学正解，以此作为训练样本，通过逐次训练6输入、6输出、2个隐含层的BP神经网络，得到机器人从工作空间到关节变量空间的非线性映射，从而实现了水轮机修复专用机器人运动学逆解的计算。     

平面柔性多体系统完全动力学问题的回转键合图法

介绍平面柔性多体系统完全动力学问题的回转键合图法。给出了综合考虑刚弹性及多种能域相互耦合的平面柔性多体系统键合图模型的建立方法,推导出了便于计算机自动生成的系统状态方程及运动副约束反力方程的统一公式,克服了非线性几何约束及微分因果关系给建立系统状态方程及运动副约束反力方程所带来的代数环问题。回转键合图法特别适合于多种能域并存的系统。通过实例说明了方法的有效性。     

Observer-based wheelbase preview control of active vehicle suspensions

Optimal observer-based wheelbase preview regulator problem is investigated for active vehicle suspension systems. It is shown that the problem reduces to the classical linear quadratic Gaussian problem, whose solution is well defined, by augmenting dynamics of system and road inputs. The resulting optimal controller is in the form of augmented state feedback controller and this augmented state is estimated by Kalman-Bucy filter using dynamics of the augmented system. Numerical examples of a half car model are given to verify the performance improvement achievable with the proposed controller.     

Tuning the Model Predictive Control of a Crude Distillation Unit

Tuning the parameters of the Model Predictive Control (MPC) of an industrial Crude Distillation Unit (CDU) is considered here. A realistic scenario is depicted where the inputs of the CDU system have optimizing targets, which are provided by the Real Time Optimization layer of the control structure. It is considered the nominal case, in which both the CDU model and the MPC model are the same. The process outputs are controlled inside zones instead of at fixed set points. Then, the tuning procedure has to define the weights that penalize the output error with respect to the control zone, the weights that penalize the deviation of the inputs from their targets, as well as the weights that penalize the input moves. A tuning approach based on multi-objective optimization is proposed and applied to the MPC of the CDU system. The performance of the controller tuned with the proposed approach is compared through simulation with the results of an existing approach also based on multi-objective optimization. The simulation results are similar, but the proposed approach has a computational load significantly lower than the existing method. The tuning effort is also much lower than in the conventional practical approaches that are usually based on ad-hoc procedures.     

ARTIFICIAL NEURAL NETWORK BASED FAULT DIAGNOSTICS OF ROLLING ELEMENT BEARINGS USING TIME-DOMAIN FEATURES

A procedure is presented for fault diagnosis of rolling element bearings through artificial neural network (ANN). The characteristic features of time-domain vibration signals of the rotating machinery with normal and defective bearings have been used as inputs to the ANN consisting of input, hidden and output layers. The features are obtained from direct processing of the signal segments using very simple preprocessing. The input layer consists of five nodes, one each for root mean square, variance, skewness, kurtosis and normalised sixth central moment of the time-domain vibration signals. The inputs are normalised in the range of 0.0 and 1.0 except for the skewness which is normalised between −1.0 and 1.0. The output layer consists of two binary nodes indicating the status of the machine—normal or defective bearings. Two hidden layers with different number of neurons have been used. The ANN is trained using backpropagation algorithm with a subset of the experimental data for known machine conditions. The ANN is tested using the remaining set of data. The effects of some preprocessing techniques like high-pass, band-pass filtration, envelope detection (demodulation) and wavelet transform of the vibration signals, prior to feature extraction, are also studied. The results show the effectiveness of the ANN in diagnosis of the machine condition. The proposed procedure requires only a few features extracted from the measured vibration data either directly or with simple preprocessing. The reduced number of inputs leads to faster training requiring far less iterations making the procedure suitable for on-line condition monitoring and diagnostics of machines.     

Data-driven modeling and predictive control for boiler–turbine unit using fuzzy clustering and subspace methods

This paper develops a novel data-driven fuzzy modeling strategy and predictive controller for boiler–turbine unit using fuzzy clustering and subspace identification (SID) methods. To deal with the nonlinear behavior of boiler–turbine unit, fuzzy clustering is used to provide an appropriate division of the operation region and develop the structure of the fuzzy model. Then by combining the input data with the corresponding fuzzy membership functions, the SID method is extended to extract the local state-space model parameters. Owing to the advantages of the both methods, the resulting fuzzy model can represent the boiler–turbine unit very closely, and a fuzzy model predictive controller is designed based on this model. As an alternative approach, a direct data-driven fuzzy predictive control is also developed following the same clustering and subspace methods, where intermediate subspace matrices developed during the identification procedure are utilized directly as the predictor. Simulation results show the advantages and effectiveness of the proposed approach.     

非惯性系柔性平面连杆机构系统完全动力学问题的回转键合图法

介绍了非惯性系柔性机械系统完全动力学问题的回转键合图法,给出了非惯性系下综合考虑刚、弹性及多种能域相互耦合的柔性机械系统键合图模型的建立方法。基于回转键合图理论,推导出便于计算机自动生成的系统状态方程及运动副约束反力方程的统一公式,有效地克服了微分因果关系及非线性结型结构给在计算机上自动建立系统状态方程及运动副约束反力方程所带来的十分困难的代数问题。所述方法特别适合于多能域并存的系统。结合实例来说明本文方法的有效性及通用性。     

双臂弹性单腿机器人的垂直跳跃控制

提出一种新型弹性单腿跳跃机器人系统,该机器人由两个驱动臂和一个弹性被动伸缩腿组成,系统只能依靠内部动力学耦合实现动态站立平衡、起跳、稳定连续跳跃运动.给出系统机构模型,分析该系统的变约束特征.该机器人系统在支撑相是二阶非完整约束系统,在飞行相是一阶非完整约束系统.针对这种欠驱动非完整约束动力学系统,采用时变非线性输入变换,提出一种实现垂直方向连续跳跃的运动控制算法.以控制腿部的姿态和振动规律、系统动量为目标实现机器人的全状态稳定控制.通过计算仿真模拟,验证提出的运动控制方案是可行的.该研究以探索弹性欠驱动机械系统振动能量循环利用技术为目标,研究结果对设计新型弹性欠驱动机械系统以及探索它在航天领域的应用具有一定参考价值.     

Cascaded Kalman and particle filters for photogrammetry based gyroscope drift and robot attitude estimation

Based on a cascaded Kalman–Particle Filtering, gyroscope drift and robot attitude estimation method is proposed in this paper. Due to noisy and erroneous measurements of MEMS gyroscope, it is combined with Photogrammetry based vision navigation scenario. Quaternions kinematics and robot angular velocity dynamics with augmented drift dynamics of gyroscope are employed as system state space model. Nonlinear attitude kinematics, drift and robot angular movement dynamics each in 3 dimensions result in a nonlinear high dimensional system. To reduce the complexity, we propose a decomposition of system to cascaded subsystems and then design separate cascaded observers. This design leads to an easier tuning and more precise debugging from the perspective of programming and such a setting is well suited for a cooperative modular system with noticeably reduced computation time. Kalman Filtering (KF) is employed for the linear and Gaussian subsystem consisting of angular velocity and drift dynamics together with gyroscope measurement. The estimated angular velocity is utilized as input of the second Particle Filtering (PF) based observer in two scenarios of stochastic and deterministic inputs. Simulation results are provided to show the efficiency of the proposed method. Moreover, the experimental results based on data from a 3D MEMS IMU and a 3D camera system are used to demonstrate the efficiency of the method.     

Temporally local recurrent radial basis function network for modeling and adaptive control of nonlinear systems

In this paper, a novel temporally local recurrent radial basis function network for modeling and adaptive control of nonlinear systems is proposed. The proposed structure consists of recurrent hidden neurons having weighted self-feedback loops and a weighted linear feed-through from the input layer directly to the output layer neuron(s). The dynamic back-propagation algorithm is developed and used for updating the parameters of the proposed structure. To improve the performance of learning algorithm, discrete Lyapunov stability method is used to develop an adaptive learning rate scheme. This scheme ensures the faster convergence of the parameters and maintains the stability of the system. A total of 5 complex nonlinear systems are used to test and compare the performance of the proposed network with other neural network structures. The disturbance rejection tests are also carried out to check whether the proposed scheme is able to handle the external disturbance/noise signals effects or not. The obtained results show the efficacy of the proposed method.