Adaptive nonlinear control using input normalized neural networks

An adaptive feedback linearization technique combined with the neural network is addressed to control uncertain nonlinear systems. The neural network-based adaptive control theory has been widely studied. However, the stability analysis of the closed-loop system with the neural network is rather complicated and difficult to understand, and sometimes unnecessary assumptions are involved. As a result, unnecessary assumptions for stability analysis are avoided by using the neural network with input normalization technique. The ultimate boundedness of the tracking error is simply proved by the Lyapunov stability theory. A new simple update law as an adaptive nonlinear control is derived by the simplification of the input normalized neural network assuming the variation of the uncertain term is sufficiently small.     

压电工作台的神经网络建模与控制

建立了压电工作台的神经网络在线辨识模型并设计了相应的自适应控制器以抑制压电工作台迟滞特性、蠕变特性及动态特性对其微定位精度的影响.采用双Sigmoid激活函数对神经网络激活函数进行了改进,同时分析了改进激活函数的神经网络模型与PI迟滞模型在迟滞建模上的异同.设计了基于改进激活函数的3层BP神经网络作为压电工作台的在线辨识模型,推导了网络权值、阈值及激活函数阈值修正公式.最后,基于神经网络模型设计了压电工作台的自适应控制方案,该控制方案利用另外一个神经网络来完成对PID控制器参数的自适应调整.实验结果表明:提出的神经网络在线辨识模型平均误差为0.095 μm,最大误差为0.32 μm;自适应控制方案跟踪三角波的平均误差为0.070 μm,最大误差为0.100 μm;跟踪复频波的平均误差为0.80 μm,最大误差为0.105 μm.实验数据显示压电工作台的定位精度得到了有效提高.     

Statistical process control with intelligence using fuzzy ART neural networks

With the automation development of manufacturing processes, artificial intelligence technology has been gradually employed to increase the automation and intelligence degree in quality control using statistical process control (SPC) method. In this paper, an SPC method based on a fuzzy adaptive resonance theory (ART) neural network is presented. The fuzzy ART neural network is applied to recognize the special disturbance of the manufacturing processes based on the classification on the histograms, which shows that the fuzzy ART neural network can adaptively learn the features of the histograms of the quality parameters in manufacturing processes. As a result, the special disturbance can be automatically detected when a feature of the special disturbance starts to appear in the histograms. At the same time, combined with spectrum analysis of the autoregressive model of quality parameters, the fuzzy ART neural network can also be utilized to adaptively detect the abnormal patterns in the control chart.     

Statistical process control with intelligence using fuzzy ART neural networks

With the automation development of manufacturing processes, artificial intelligence technology has been gradually employed to increase the automation and intelligence degree in quality control using statistical process control (SPC) method. In this paper, an SPC method based on a fuzzy adaptive resonance theory (ART) neural network is presented. The fuzzy ART neural network is applied to recognize the special disturbance of the manufacturing processes based on the classification on the histograms, which shows that the fuzzy ART neural network can adaptively learn the features of the histograms of the quality parameters in manufacturing processes. As a result, the special disturbance can be automatically detected when a feature of the special disturbance starts to appear in the histograms. At the same time, combined with spectrum analysis of the autoregressive model of quality parameters, the fuzzy ART neural network can also be utilized to adaptively detect the abnormal patterns in the control chart.     

Improved recognition of control chart patterns using artificial neural networks

Recognition of abnormal patterns in control charts provides clues to reveal potential quality problems in the manufacturing processes. One potentially popular approach for recognizing different control chart patterns (CCPs) is to develop heuristics based on various shape features of the patterns. The advantage of this approach is that the users can easily understand how a particular pattern is identified. However, consistency in the recognition performance is found to be considerably poor in the heuristics approach. Since shape features represent the main characteristics of the patterns in a condensed form, artificial neural network (ANN) with features extracted from the process data as input vector representation can facilitate efficient pattern recognition with a smaller network size. In this paper, a set of seven shape features is selected, whose magnitudes are independent of the process mean and standard deviation under a special representation of the sampling interval in the control chart plot. Based on these features, the CCPs are recognized using a multilayered perceptron neural network trained by back-propagation algorithm. The recognizer can recognize all the eight commonly observed CCPs. Extensive performance evaluation of this recognizer is carried out using simulated pattern data. Numerical results indicate that the developed ANN recognizer can perform well in real time process control applications with respect to both recognition accuracy and consistency.     

Statistical process control using optimized neural networks: A case study

The most common statistical process control (SPC) tools employed for monitoring process changes are control charts. A control chart demonstrates that the process has altered by generating an out-of-control signal. This study investigates the design of an accurate system for the control chart patterns (CCPs) recognition in two aspects. First, an efficient system is introduced that includes two main modules: feature extraction module and classifier module. In the feature extraction module, a proper set of shape features and statistical feature are proposed as the efficient characteristics of the patterns. In the classifier module, several neural networks, such as multilayer perceptron, probabilistic neural network and radial basis function are investigated. Based on an experimental study, the best classifier is chosen in order to recognize the CCPs. Second, a hybrid heuristic recognition system is introduced based on cuckoo optimization algorithm (COA) algorithm to improve the generalization performance of the classifier. The simulation results show that the proposed algorithm has high recognition accuracy.     

Nonlinear model identification and adaptive model predictive control using neural networks

This paper presents two new adaptive model predictive control algorithms, both consisting of an on-line process identification part and a predictive control part. Both parts are executed at each sampling instant. The predictive control part of the first algorithm is the Nonlinear Model Predictive Control strategy and the control part of the second algorithm is the Generalized Predictive Control strategy. In the identification parts of both algorithms the process model is approximated by a series-parallel neural network structure which is trained by a recursive least squares (ARLS) method. The two control algorithms have been applied to: 1) the temperature control of a fluidized bed furnace reactor (FBFR) of a pilot plant and 2) the auto-pilot control of an F-16 aircraft. The training and validation data of the neural network are obtained from the open-loop simulation of the FBFR and the nonlinear F-16 aircraft models. The identification and control simulation results show that the first algorithm outperforms the second one at the expense of extra computation time.     

基于神经网络技术的数字信号处理飞控系统设计

针对无人机性能指标和体积限制,设计一种基于TMS320C5402型数字信号处理器的新型飞控系统.详细阐述系统的设计思想以及软、硬件结构和控制策略,给出相应的飞控流程图与神经网络动态逆控制原理图.通过在环回路仿真验证,所设计的系统具有计算速度快、可靠性好等优点,能够赋予无人机更大的机动性和更广泛的适用性.     

Adaptive control of nonlinear system using online error minimum neural networks

In this paper, a new learning algorithm named OEM-ELM (Online Error Minimized-ELM) is proposed based on ELM (Extreme Learning Machine) neural network algorithm and the spreading of its main structure. The core idea of this OEM-ELM algorithm is: online learning, evaluation of network performance, and increasing of the number of hidden nodes. It combines the advantages of OS-ELM and EM-ELM, which can improve the capability of identification and avoid the redundancy of networks. The adaptive control based on the proposed algorithm OEM-ELM is set up which has stronger adaptive capability to the change of environment. The adaptive control of chemical process Continuous Stirred Tank Reactor (CSTR) is also given for application. The simulation results show that the proposed algorithm with respect to the traditional ELM algorithm can avoid network redundancy and improve the control performance greatly.     

Multivariable alarming using neural networks

The monitoring and alarming of processes is normally done in one dimension. Each measurable parameter is treated as independent of all others. The only time this is not true is when the dynamics of a multivariable process are "modeled" using equations that predict the chemical, physical, and/or thermodynamic properties of the process in terms of these parameters. Unfortunately, this requires that the relationship be known and accurately describable in mathematical terms. Using neural networks to map the "N"-space relationship among a set of "N"-variables, it is possible to create experience-based "models" of the multivariable relationships. This technique does not require that the relationship even be known, only that a "live" process be available to "teach" the neural network the various safe and unsafe states of the process.     

Tolerance allocation using neural networks

The purpose of tolerance allocation is to find a combination of tolerances to individual components such that the assembly tolerance constraint is met with minimum production cost. There are several methods available to allocate or apportion the assembly tolerance to individual parts. Some of the most common methods use linear programming, Lagrange multipliers, exhaustive search and statistical distributions. However, all the methods have some limitations. Moreover, most of these methods cannot account for the frequently observed mean shift phenomena that occur owing to tool wear, chatter, bad coolant, etc. This paper presents a neural networks-based approach for the tolerance allocation problem considering machines' capabilities, and mean shifts. The network is trained using the backpropagation learning method and used to predict individual part tolerances.     

压电陶瓷执行器的神经网络实时自适应逆控制

目的：为了提高压电陶瓷执行器执行精度,提出消除压电陶瓷的非线性、非光滑的迟滞特性的方法。 方法：提出了基于内积的压电陶瓷动态神经网络非线性、非光滑的迟滞逆模型,采用反馈误差学习方法,避免了求取压电陶瓷的Jacobian信息,快速地在线得到压电陶瓷的逆模型,并结合PID反馈控制,在dSPACE系统平台上,实现压电陶瓷的神经网络自适应逆控制,为了提高实时性,程序采用效率高、速度快的C-MEX S Function编程。结果：实验结果表明：神经网络自适应逆控制的控制精度为：0.13μm,而PID控制精度为：0.32μm 。结论：所提出方法有效地消除了迟滞的影响,控制精度高。     

数控机床轴控制器非线性特性神经网络建模

为了消除数控机床系统轴控制中存在的反向间隙问题,本文通过引入一个特殊的迟滞因子,将多映射的非线性转换成一一映射,然后建立基于神经网络的反向间隙非线性模型。该模型结构简单,简化了辨识过程,可以调整神经网络权值以适应不同条件下的迟滞辨识,较好地解决了反向间隙类非线性的控制问题。     

群控电梯前向神经网络控制方法

通过构造用于派梯选择的评价函数 ,在建立隶属度函数的基础上 ,利用前向神经网络自学习功能获得评价函数中各个因素的最佳加权系数 ,实现最佳派梯。仿真和实际应用结果表明了本控制方法的可行性及优良效果。     

Identifying change point of a non-random pattern on control chart using artificial neural networks

An important step in root cause analysis is the identification of the time when process first changed. The time when a disturbance first manifested itself into the process is referred to as change point. Identification of the change point could help process engineer to perform root cause analysis effectively. In this paper, an estimator for the change point of a normal process mean using artificial neural network (ANN) is proposed. Five patterns of change namely single step, linear trend, systematic, cyclic, and mixture are studied. Whenever possible, results are compared numerically to the results obtained by other methods proposed by different researchers. First the type of change to be recognized by an ANN-based pattern recognizer is identified and then the change point in the process mean is estimated. Results indicate satisfactory performance for the proposed method that could be used as an effective method for root cause analysis by process engineer.     

Precision position control of servo systems using adaptive back-stepping and recurrent fuzzy neural networks

To improve position tracking performance of servo systems, a position tracking control using adaptive back-stepping control(ABSC) scheme and recurrent fuzzy neural networks(RFNN) is proposed. An adaptive rule of the ABSC based on system dynamics and dynamic friction model is also suggested to compensate nonlinear dynamic friction characteristics. However, it is difficult to reduce the position tracking error of servo systems by using only the ABSC scheme because of the system uncertainties which cannot be exactly identified during the modeling of servo systems. Therefore, in order to overcome system uncertainties and then to improve position tracking performance of servo systems, the RFNN technique is additionally applied to the servo system. The feasibility of the proposed control scheme for a servo system is validated through experiments. Experimental results show that the servo system with ABS controller based on the dual friction observer and RFNN including the reconstruction error estimator can achieve desired tracking performance and robustness.     

Simulation of surface generated during abrasive flow finishing of Al/SiCp-MMC using neural networks

Abrasive flow machining (AFM) is a multivariable finishing process which finds its use in difficult to finish surfaces on difficult to finish materials. Near accurate prediction of generated surface by this process could be very useful for the practicing engineers. Conventionally, regression models are used for such prediction. This paper presents the use of artificial neural networks (ANN) for modeling and simulation of response characteristics during AFM process in finishing of Al/SiC_p metal matrix composites (MMCs) components. A generalized back-propagation neural network with five inputs, four outputs, and one hidden layer is designed. Based upon the experimental data of the effects of AFM process parameters, e.g., abrasive mesh size, number of finishing cycles, extrusion pressure, percentage of abrasive concentration, and media viscosity grade, on performance characteristics, e.g., arithmetic mean value of surface roughness (R _a, micrometers), maximum peak–valley surface roughness height (R _t, micrometers), improvement in R _a (i.e., ΔR _a), and improvement in R _t (i.e., ΔR _t), the networks are trained for finishing of Al/SiC_p-MMC cylindrical components. ANN models are compared with multivariable regression analysis models, and their prediction accuracy is experimentally validated.     

Visual feedback control of a robot in an unknown environment (learning control using neural networks)

In this paper, a visual feedback control approach based on neural networks is presented for a robot with a camera installed on its end-effector to trace an object in an unknown environment. First, the one-to-one mapping relations between the image feature domain of the object to the joint angle domain of the robot are derived. Second, a method is proposed to generate a desired trajectory of the robot by measuring the image feature parameters of the object. Third, a multilayer neural network is used for off-line learning of the mapping relations so as to produce on-line the reference inputs for the robot. Fourth, a learning controller based on a multilayer neural network is designed for realizing the visual feedback control of the robot. Last, the effectiveness of the present approach is verified by tracing a curved line using a 6-degrees-of-freedom robot with a CCD camera installed on its end-effector. The present approach does not necessitate the tedious calibration of the CCD camera and the complicated coordinate transformations. This revised version was published online in October 2004 with a correction to the issue number.     

Effective control of optimum dressing according to gap increase by using multilayered neural networks

Dressing of superabrasive wheels capable of producing a good mirror finish on brittle materials is a current requirement.A neural identifier and a neural controller for optimum control of electro-discharge dressing systems are proposed for this purpose.The modelling of the system and an actual plant control system for mirror-like grinding is obtained from a neural identifier and a neural control structure giving satisfactory stability is proposed. The results of this study using multilayered neural networks show that the proposed neural identifier not only gives accurate results but can also find the relationship parameters for the electro-discharge dressing system. Additionally, the proposed neural controller gives very effective control by gap increase using a learning process in spite of the nonlinear characteristics of the electro-discharge conditions.     

Controlling a robot's position using neural networks

In order to fully utilise the power of robots in factories, robot process capability (RPC) must be considered and improved. To improve the RPC in on-line processing by applying robot learning, the counterpropagation network was modified in this research. With two layers, the counterpropagation network was modified to control a robot's gross and fine motions. For the first layer, the network serves as a sensor-signal generator to control the gross motion. For the second layer, the network serves as a fine motion adjuster. Also, each layer can be separated functionally. By controlling both the gross and the fine motions, the RPC can then be improved. The modified two-layer counterpropagation network control scheme was validated by computer simulation and physical implementation on a RS-2200 robot system.