Hybrid H_2/H_∞ force/position control based on neural networks

Ifitisnecessaryforarobottocontactitsoperatingenvironmentwhenitexecutessometasks ,suchasassembling ,polishing ,edgefollowingandcutting ,itrequiresaforcecontrolinordertoachievethebestresult.RaibertandCraigfirstbroughtforwardhybridposition/forcecontrolstrategies .Withthisframework ,therehavebeenmanyscholarswhohaveproposedvariousnewcontrolstrategies ,suchasadaptivecontrol,slidingcontrolandrobustcontrol,etc .Inrecent years,neuralnetworkandfuzzycontrol[1 ,2 ] havebeenextensivelystudiedfortheiruseint…     

Hybrid He／H∞ force／position control based on neural networks

A neural network control scheme with mixed H2/H∞ performance was proposed for robot force/position control under parameter uncertainties and external disturbances. The mixed H2/H∞ tracking performance ensures both robust stability under a prescribed attenuation level for external disturbance and H2 optimal tracking. The neural network was introduced to adaptively estimate nonlinear uncertainties, improving the system‘ s performance under parameter uncertainties as well as obtaining the H2/H∞ tracking performance. The simulation shows that the control method performs better even when the system is under large modeling uncertainties and external disturbances.     

Proton exchange membrane fuel cells modeling based on artificial neural networks

To understand the complexity of the mathematical models of a proton exchange membrane fuel cell (PEMFC) and their shortage of practical PEMFC control, the PEMFC complex mechanism and the existing PEMFC models are analyzed, and artificial neural networks based PEMFC modeling is advanced. The structure, algorithm, training and simulation of PEMFC modeling based on improved BP networks are given out in detail. The computer simulation and conducted experiment verify that this model is fast and accurate, and can be used as a suitable operational model for PEMFC real-time control.     

Robustness-tracking control based on sliding mode and H∞ theory for linear servo system

A robustness-tracking control scheme based on combining H∞ robust control and sliding mode control is proposed for a direct drive AC permanent-magnet linear motor servo system to solve the conflict between tracking and robustness of the linear servo system. The sliding mode tracking controller is designed to ensure the system has a fast tracking characteristic to the command, and the H∞ robustness controller suppresses the disturbances well within the close loop( including the load and the end effect force of linear motor etc. ) and effectively minimizes the chattering of sliding mode control which influences the steady state performance of the system. Simulation results show that this control scheme enhances the track-command-ability and the robustness of the linear servo system, and in addition, it has a strong robustness to parameter variations and resistance disturbances.     

Robustness-tracking control based on sliding mode and H∞ theory for linear servo system

A robustness-tracking control scheme based on combining H∞ robust control and sliding mode control is proposed for a direct drive AC permanent-magnet linear motor servo system to solve the conflict between tracking and robustness of the linear servo system. The sliding mode tracking controller is designed to ensure the system has a fast tracking characteristic to the command, and the H∞ robustness controller suppresses the disturbances well within the close loop( including the load and the end effect force of linear motor etc. ) and effectively minimizes the chattering of sliding mode control which influences the steady state performance of the system. Simulation results show that this control scheme enhances the track-command-ability and the robustness of the linear servo system, and in addition, it has a strong robustness to parameter variations and resistance disturbances.     

Flux-measuring approach of high temperature metal liquid based on BP neural networks

A soft-measuring approach is presented to measure the flux of liquid zinc with high temperature and causticity. By constructing mathematical model based on neural networks, weighing the mass of liquid zinc, the flux of liquid zinc is acquired indirectly, the measuring on line and flux control are realized. Simulation results and industrial practice demonstrate that the relative error between the estimated flux value and practical measured flux value is lower than 1.5%, meeting the need of industrial process.     

A new semi-active suspension control strategy through mixed H2/H∞ robust technique

A new semi-active suspension control strategy through mixed H2/H∞ robust technique was developed due to its flexibility and robustness to model uncertainties.A full car model with seven degrees of freedom was established to demonstrate the effectiveness of the new control approach.Magneto-rheological(MR) dampers were designed,manufactured and characterized as available semi-active actuators in the developed semi-active suspension system.The four independent mixed H2/H∞ controllers were devised in order to p...     

Pulse frequency classification based on BP neural network

In Traditional Chinese Medicine (TCM), it is an important parameter of the clinic disease diagnosis to analysis the pulse frequency. This article accords to pulse eight major essentials to identify pulse type of the pulse frequency classification based on back-propagation neural networks (BPNN). The pulse frequency classification includes slow pulse, moderate pulse, rapid pulse etc. By feature parameter of the pulse frequency analysis research and establish to identify system of pulse frequency features. The pulse signal from detecting system extracts period, frequency etc feature parameter to compare with standard feature value of pulse type. The result shows that identify-rate attains 92.5% above.     

Short-term load forecasting based on fuzzy neural network

The fuzzy neural network is applied to the short-term load forecasting. The fuzzy rules and fuzzy membership functions of the network are obtained through fuzzy neural network learming. Three inference algorithms, i.e. themultiplicative inference, the maximum inference and the minimum inference, are used for comparison. The learningalgorithms corresponding to the inference methods are derived from back-propagation algorithm. To validate the fuzzyneural network model, the network is used to Predict short-term load by compaing the network output against the realload data from a local power system supplying electricity to a large steel manufacturer. The experimental results aresatisfactory.     

Study on mixed H_2/H_∞ robust control strategy of four wheel steering system

Four wheel steering(4 WS) technology can effectively improve the vehicle handling stability and driving safety. In order to fully consider the influence of the rear wheel steering, the vehicle dynamics model of 4 WS vehicle, including the rear wheel steering by wire and two degrees of freedom vehicle model of 4 WS vehicle, is established in this paper. The desired yaw rate is obtained according to the variable transmission ratio strategy. The yaw rate tracking strategy is applied to 4 WS vehicle and rear wheel steering resistance moment is taken into account. Based on the robust control theory, H_2/H_∞ mixed robust controller design is carried to research the stability control of 4 WS vehicle. Finally, the closed-loop simulation added driver model based on preview theory is carried out. The simulation results indicate that the designed H_2/H_∞ mixed robust controller can achieve the stability control.     

Cement industry control system based on multi agent

Cement production is characterized by its great capacity, long-time delay, multi variables, difficult measurement and multi disturbances. According to the distributed intelligent control strategy based on the multi agent, the multi agent control system of cement production is built, which includes integrated optimal control and diagnosis control. The distributed and multiple level structure of multi agent system for the cement control is studied. The optimal agent is in the distributed state, which aims at the partial process of the cement production, and forms the optimal layer. The diagnosis agent located on the diagnosis layer is the diagnosis unit which aims at the whole process of the cement production, and the central management unit of the system. The system cooperation is realized by the communication among optimal agents and diagnosis agent. The architecture of the optimal agent and the diagnosis agent are designed. The detailed functions of the optimal agent and the diagnosis agent are analyzed.At last the realization methods of the agents are given, and the application of the multi agent control system is presented. The multi agent system has been successfully applied to the off-line control of one cement plant with capacity of 5000 t/d. The results show that the average yield of the clinker increases 9.3% and the coal consumption decreases 7.5 kg/t.     

离散系统具有域极点约束的H2/H∞滤波

主要讨论了具有域极点约束的离散时不变系统的混合H2／H∞滤波问题。首先,研究了系统传递函数的H2范数以及H∞范数;然后,给出了用LMI形式描述的在任意圆域的极点配置公式;最后,根据H2,H∞范数性能指标和圆域约束条件,建立了一种混合H2／H∞滤波器的设计方法。     

ART-2 neural network based on eternal term memory vector： Architecture and algorithm

Aimed at the problem that the traditional ART-2 neural network can not recognize a gradually changing course, an eternal term memory (ETM) vector is introduced into ART-2 to simulate the function of human brain, i.e. the deep remembrance for the initial impression.. The eternal term memory vector is determined only by the initial vector that establishes category neuron node and is used to keep the remembrance for this vector for ever. Two times of vigilance algorithm are put forward, and the posterior input vector must first pass the first vigilance of this eternal term memory vector, only succeeded has it the qualification to begin the second vigilance of long term memory vector. The long term memory vector can be revised only when both of the vigilances are passed. Results of recognition examples show that the improved ART-2 overcomes the defect of traditional ART-2 and can recognize a gradually changing course effectively.     

Clustering in mobile ad hoc network based on neural network

1 INTRODUCTION Multi-hop wireless network is an ideal technology to establish an instant communication infrastructure for civilian and military applications. Its applications include collaborative, distributed mobile computing, disaster recovery, law enforcement (crowd control, search and rescue), digital battlefield communications, and so on[1]. Such situations demand a network where all the nodes including the base stations are potentially mobile, and communication must be supported unwi…     

Robust H∞ directional control for a sampled-data autonomous airship

A robust H∞ directional controller for a sampled-data autonomous airship with polytopic parameter uncertainties was proposed. By input delay approach, the linearized airship model was transformed into a continuous-time system with time-varying delay. Sufficient conditions were then established based on the constructed Lyapunov-Krasovskii functional, which guarantee that the system is mean-square exponentially stable with H∞ performance. The desired controller can be obtained by solving the obtained conditions. Simulation results show that guaranteed minimum H∞ performance γ=1.4037 and fast response of attitude for sampled-data autonomous airship are achieved in spite of the existence of parameter uncertainties.     

Networked control and supervision system based on LonWorks fieldbus and Intranet/Internet

A networked control and supervision system （NCSS） based on LonWorks fieldbus and lntranet/Intemet was designed, which was composed of the universal intelligent control nodes （ICNs）, the visual control and supervision configuration platforms （VCCP and VSCP） and an Intranet/Internet-based remote supervision platform （RSP）. The ICNs were connected to field devices, such as sensors, actuators and controllers. The VCCP and VSCP were implemented by means of a graphical programming environment and network management so as to simplify the tasks of programming and maintaining the ICNs. The RSP was employed to perform the remote supervision function, which was based on a three-layer browser/server（B/S） structure mode. The validity of the NCSS was demonstrated by laboratory experiments.     

A complex control system based on the fuzzy PID control and state predictor feedback control

A multi-mode adaptive controller was proposed. The controller features in the combination of Bang-bang and Fuzzy PID controls with state predictor. When large error exists, the controller operates in Bang-bang mode, otherwise it works as a fuzzy PID controller. For only few parameters to be adjusted, the real time controlled system achieveed good stability and fast response. Furthermore, the introduction of state observer was also discussed to extend the capability of the proposed controller to the plant with time-delay factors. The classical PID controller and the multi-mode controller were applied to the same second-order system successively. By comparison of the simulation results, the effectiveness of the controller were shown. At last, on electric-wire production line, this approach was practiced to control electric-wire diameter with an additive random disturbance signal. The test result further proved the effectiveness of the multi-mode controller.     

模糊时滞系统基于状态反馈的H2/H∞控制

考虑一类连续模糊时滞系统基于状态反馈的H2/H∞控制问题.目的是设计模糊状态反馈控制器,使得闭环系统渐近稳定,且闭环系统满足给定的H∞性能指标,同时给定的二次成本函数有上界.利用线性矩阵不等式方法,给出了该问题可解的充分条件.分析表明,期望的状态反馈控制器可通过求解一组给定的线性矩阵不等式而得到.仿真结果验证了所提出方法的有效性.     

直接驱动电动舵机的混合H2/H∞控制器设计

介绍了一种基于有限转角力矩电机的导弹电动舵机的组成及工作原理，针对直接驱动系统易受负载扰动及参数变化影响的特点，利用H2控制保证系统动态性能以及H∞控制在对象存在模型及参数不确定性、未建模动态和有界扰动时可以保证系统全局稳定的特性，设计了舵机的混合H2／H∞控制器。仿真结果及分析表明，系统对参数变化及外部扰动具有鲁棒稳定性和较强的鲁棒跟踪能力。