Neural network modelling and control strategies for a pH process

The control of a pH process using neural networks is examined. The neural network as a universal approximator is used to good effect in this nonlinear problem, as is shown in the simulation results. In the modelling task, the dynamics of the process was carefully examined to determine a suitable structure for the net. In particular, a multilayer net consisting of two single hidden layers was constructed to reflect the Wiener model of the pH process. This led to much simpler training compared to similar modelling attempts by other researchers. For the control task, two schemes were simulated. In one approach, a net was used to deal with the static nonlinearity to achieve control over a wide working range. The dynamic controller used was the PID, with its parameters tuned on a relay auto-tuner. This control design was compared with the strong acid equivalent method. In the second approach, a direct model reference adaptive neural network control scheme was proposed. The training procedure uses the more efficient least squares algorithm developed by Loh and Fong.     

Predictive control of a real-world Diesel engine using an extended online active set strategy

In order to meet tight emission limits Diesel engines are nowadays equipped with additional hardware components like an exhaust gas recirculation valve and a variable geometry turbocharger. Conventional engine control units use two SISO control loops to regulate the exhaust gas recirculation valve and the variable geometry turbocharger, although their effects are highly coupled. Moreover, these actuators are subject to physical constraints which seems to make an advanced control approach like model predictive control (MPC) the method of choice. In order to deal with MPC sampling times in the order of milliseconds, we employed an extension of the recently developed online active set strategy for controlling a real-world Diesel engine in a closed-loop manner. The results show that predictive engine control based on online optimisation can be accomplished in real-time – even on cheap controller hardware – and leads to increased controller performance.     

基于神经网络的柴油机故障诊断方法

提出了一种基于三层BP网络的柴油机故障诊断模型，给出了一种基于黄金分割法的变步长学习算法。仿真结果表明，该算法比标准BP算法具有更快的学习速度，完全适用于柴油机故障诊断系统。     

Diesel engine air path control based on neural approximation of nonlinear MPC

This paper deals with a control design problem for a diesel engine air path system that has strong nonlinearity and requires multi-input and multi-output control to satisfy requirements and constraints. We focus on a neural network based approximation of nonlinear model predictive control (NMPC) for high-speed computation. Most neural approximation methods are verified only through simulation; further, the influence of approximation on the closed-loop performance has been not sufficiently discussed. In this study, we discuss this influence, and propose a new method to improve stability against degradation due to an approximation error. The control system is assembled using a neural network based controller, obtained by the proposed method, and an unscented Kalman filter. This system is verified both numerically and experimentally; the results demonstrate the capability of the proposed method to track the boost pressure, EGR rate, and pumping loss according to the reference values, and satisfy the constraints of compressor surge and choke. The high computation speed that can be achieved using a standard on-board ECU is also demonstrated using the approximated controller.     

输入饱和与姿态受限的四旋翼无人机反步姿态控制

本文针对四旋翼无人机研究了鲁棒反步姿态控制策略.由于四旋翼无人机结构复杂,其非线性数学模型难以精确建立,因此在控制器设计过程中需要综合考虑模型不确定性、未知外部干扰、输入饱和以及姿态受限等因素.针对模型中的不确定项,使用神经网络进行逼近;对于外部未知干扰,使用非线性干扰观测器进行补偿;使用双曲正切函数逼近饱和函数,解决输入饱和问题;同时使用界限Lyapunov函数设计控制器,确保姿态满足限制条件.最后,设计四旋翼无人机反步姿态控制器,并根据Lyapunov稳定性定理证明了闭环控制系统的有界稳定.仿真结果表明了所研究控制方法的有效性.     

Mass flow estimation with model bias correction for a turbocharged Diesel engine

A systematic design method for mass flow estimation with correction for model bias is proposed. Based on an augmented observable Mean Value Engine Model (MVEM) of a turbocharged Diesel engine, the online estimation of states with additional biases is performed to compute the mass flows for different places. A correction method is applied, that utilizes estimated biases which are in a least-square sense redistributed between the correction terms to the uncertain mass flow maps and then added to the estimated mass flows. An Extended Kalman Filter (EKF) is tested off-line on production car engine data where the combination of an intake manifold pressure sensor, exhaust manifold pressure sensor and turbocharger speed sensor is compared and discussed in different sensor fusions. It is shown that the correction method improves the uncorrected estimated air mass flow which is validated against the airflow data measured in the intake duct.     

Neural networks for control systems—A survey

This paper focuses on the promise of artificial neural networks in the realm of modelling, identification and control of nonlinear systems. The basic ideas and techniques of artificial neural networks are presented in language and notation familiar to control engineers. Applications of a variety of neural network architectures in control are surveyed. We explore the links between the fields of control science and neural networks in a unified presentation and identify key areas for future research.     

一种求解线性约束的非线性规划神经网络方法

针对线性约束的非线性规划的求解问题,利用罚函数求解优化问题的思想将其转化为二次凸规划,基于神经网络的结构特性,定义所需的能量函数,从而使网络收敛于唯一稳定点最终实现线性约束的非线性规划的求解。实验仿真结果表明,该方法是有效和正确的,且能推广到含参的非线性规划和多目标规划中去。     

基于观测器的非线性系统神经网络鲁棒控制

提出一类不依赖于模型的状态观测器，通过分析其根轨迹和极点要求配置合适的参数，该观测器本身是一个能提取高阶微分的高阶微分器．基于Lyapunov稳定性理论设计了使闭环系统渐近稳定，对模型变化和扰动具有鲁棒性的神经网络自适应控制器．该控制器不仅考虑了闭环系统的输出和设定输入误差的微分，而且考虑了误差的高阶微分，从而提高了控制品质．最后通过仿真例子验证了所提出理论的正确性．     

Automated Recurrent Neural Network Design of a Neural Controller in a Custom Power Device

A general purpose implementation of the Tabu Search metaheuristic, called Universal Tabu Search, is used to optimally design a Locally Recurrent Neural Network architecture. Indeed, the design of a neural network is a tedious and time consuming trial and error operation that leads to structures whose optimality is not guaranteed. In this paper, the problem of choosing the number of hidden neurons and the number of taps and delays in the FIR and IIR network synapses is formalised as an optimisation problem whose cost function to be minimised is the network error calculated on a validation data set. The performances of the proposed approach have been tested on the design problem of a Neural Network controller of a Custom Power protection device.     

Neural network applications for automatic new topic identification of FAST and Excite search engine transaction logs

Abstract: Content analysis of search engine user queries is an important task, since successful exploitation of the content of queries can result in the design of efficient information retrieval algorithms for more efficient search engines. Identification of topic changes within a user search session is a key issue in content analysis of search engine user queries. This study proposes an artificial neural network application in the area of search engine research to automatically identify topic changes in a user session by using statistical characteristics of queries, such as time intervals and query reformulation patterns. Sample data logs from the FAST and Excite search engines are selected to train the neural network and then the neural network is used to identify topic changes in the data log. As a result, almost all the performance measures yielded favourable results.     

Neural network methods for the modeling and control of welding processes

While welding processes are of great importance in manufacturing, their modeling and control is still subject of research. The highly nonlinear, strongly coupled, and multivariable nature of these processes renders the use of analytical tools practically impossible. In this article a novel approach is presented which employs networks of simple nonlinear units: a neural network. A widely used welding process, the Gas Tungsten Arc Welding is presented and the problem of its modeling and control is exhibited. A very brief introduction to neural networks is followed by presenting the experimental results for modeling the static and dynamic behavior of the process, as well as some practical recommendations regarding the use of the neural network techniques for controlling these processes.     

Prediction and reduction of diesel engine emissions using a combined ANN–ACO method

In this study, the combination of artificial neural network (ANN) and ant colony optimization (ACO) algorithm has been utilized for modeling and reducing NO_x and soot emissions from a direct injection diesel engine. A feed-forward multi-layer perceptron (MLP) network is used to represent the relationship between the input parameters (i.e., engine speed, intake air temperature, rate of fuel mass injected, and power) on the one hand and the output parameters (i.e., NO_x and soot emissions) on the other hand. The ACO algorithm is employed to find the optimum air intake temperatures and the rates of fuel mass injected for different engine speeds and powers with the purpose of simultaneous reduction of NO_x and soot. The obtained results reveal that the ANN can appropriately model the exhaust NO_x and soot emissions with the correlation factors of 0.98, 0.96, respectively. Further, the employed ACO algorithm gives rise to 32% and 7% reduction in the NO_x and soot, respectively. The response time of the optimization process was obtained to be less than 4 min for the particular PC system used in the present work. The high accuracy and speed of the model show its potential for application in intelligent controlling systems of the diesel engines.     

不对称约束多人非零和博弈的自适应评判控制

本文针对连续时间非线性系统的不对称约束多人非零和博弈问题, 建立了一种基于神经网络的自适应评判控制方法. 首先, 本文提出了一种新颖的非二次型函数来处理不对称约束问题, 并且推导出最优控制律和耦合Hamilton-Jacobi方程. 值得注意的是, 当系统状态为零时, 最优控制策略是不为零的, 这与以往不同. 然后, 通过构建单一评判网络来近似每个玩家的最优代价函数, 从而获得相关的近似最优控制策略. 同时, 在评判学习期间发展了一种新的权值更新规则. 此外, 通过利用Lyapunov理论证明了评判网络权值近似误差和闭环系统状态的稳定性. 最后, 仿真结果验证了本文所提方法的有效性     

Neural networks for real‐time nonlinear control of a variable geometry turbocharged diesel engine

New engines are submitted to emission standards that are becoming more and more restrictive. Diesel engines are typically equipped with variable geometry turbo‐compressor, exhaust gas recirculation system, high‐pressure common rail system and post‐treatment devices in order to meet these legislative requirements. Consequently, the control of diesel engines becomes a very difficult task involving five to 10 control variables that interact with each other and that are highly nonlinear. Until the present day, the control schemes integrated in the engine's controller are all based on static maps identified by steady‐state engine mapping. Afterward, these schemes are adjusted and calibrated in the vehicle using various control techniques in order to assure a better dynamic response of the engine under dynamic load. In this paper, we are interested in developing a mathematical optimization process that searches for the optimal control scheme under static and dynamic operating conditions. Firstly, we suggest modeling the engine and its emissions using mean value models which require limited experiments and are in good agreement with the experimental data. These models are then used in a dynamic optimization process based on the Broyden–Fletcher–Goldfarb–Shanno algorithm in order to find the optimal control scheme of the engine. The results show a reduction of the engine emissions without deteriorating its performance. Finally, we propose a practical control technique based on neural networks in order to apply these control schemes online to the engine. The results are promising. Copyright © 2007 John Wiley & Sons, Ltd.     

Air pollution modelling with the aid of computational intelligence methods in Thessaloniki, Greece

Air pollution modelling is necessary for simulating the atmospheric environment system in terms of pollutants and meteorological conditions, taking into account the nonlinearities of the underlying phenomena. In the current paper, Artificial Neural Networks are used for modelling ozone, and for simulating its behaviour in relation to other atmospheric parameters of interest, for the city of Thessaloniki, Greece. This behaviour is also investigated with the aid of Principal Component Analysis (PCA). Results suggest the operational capabilities of such models, and the research potential in the application of computational intelligence methods for the environmental sector.     

Adaptive air-fuel ratio control with MLP network

This paper presents an application of adaptive neural network model-based predictive control (MPC) to the air-fuel ratio of an engine simulation. A multi-layer perceptron (MLP) neural network is trained using two on-line training algorithms: a back propagation algorithm and a recursive least squares (RLS) algorithm. It is used to model parameter uncertainties in the nonlinear dynamics of internal combustion (IC) engines. Based on the adaptive model, an MPC strategy for controlling air-fuel ratio is realized, and its control performance compared with that of a traditional PI controller. A reduced Hessian method, a newly developed sequential quadratic programming (SQP) method for solving nonlinear programming (NLP) problems, is implemented to speed up nonlinear optimization in the MPC.     

现场总线控制系统在柴油机试验站的应用

本文介绍了一种基于现场总线体系结构的柴油机试验自动测试系统。根据现场总线控制系统和柴油机试验流程特点，提出了柴油机试验流程现场控制方案，以及采用SHCAN2000系统的设计与实现。     

Tracking control of a marine surface vessel with full-state constraints

In this paper, a trajectory tracking control law is proposed for a class of marine surface vessels in the presence of full-state constraints and dynamics uncertainties. A barrier Lyapunov function (BLF) based control is employed to prevent states from violating the constraints. Neural networks are used to approximate the system uncertainties in the control design, and the control law is designed by using the Moore-Penrose inverse. The proposed control is able to compensate for the effects of full-state constraints. Meanwhile, the signals in the closed-loop system are guaranteed to be semiglobally uniformly bounded, with the asymptotic tracking being achieved. Finally, the performance of the proposed control has been tested and verified by simulation studies.