SIMO傅里叶三角基神经网络的权值直接确定法和结构自确定算法

根据傅里叶级数逼近理论,将正交三角函数系作为隐层神经元激励函数,合理选取这些激励函数的周期参数,构造单输入多输出(SIMO)傅里叶三角基神经网络模型.根据该网络的特点,推导出一种基于伪逆的权值直接确定法,从而1步计算出网络最优权值,并在此基础上设计出隐层结构自确定算法.仿真结果表明,与传统BP(反向传播)神经网络及基于最小二乘法的SIMO傅里叶神经网络模型相比,本网络模型具有更高的计算精度和更快的计算速度.

求解无约束最优化非单调自确定信赖域算法

基于文献[1]给出的自适应信赖域算法,结合非单调技术提出一个新的求解无约束优化问题的非单调自确定信赖域算法。该算法具有全局收敛性,并在适合的条件下也得到该算法的局部超线性和二次收敛性。

多输入Sigmoid激励函数神经网络权值与结构确定法

结合伪逆直接计算得到神经元之间最优权值的方法,提出了一种双阶段自动搜索与确定最优网络结构的算法,克服了原有BP神经网络模型及其学习算法的固有缺陷。以函数逼近为例,计算机数值实验结果显示了算法有效且耗时短,证实了由该算法得到的网络对于多输入函数具有较优良的逼近(学习与校验)性能。

Hermite插值神经网络权值和结构确定理论探讨

为了克服BP神经网络固有的缺陷,基于Hermite插值理论,构造了一种新型的前向神经网络模型(即Hermite插值神经网络模型)。针对该网络模型,提出了一种基于矩阵伪逆的权值直接确定方法,并在此基础上探讨了隐神经元数目自动确定的方法(即网络结构自确定方法)。计算机仿真结果表明,相比于传统的BP神经网络,使用权值与结构双确定方法的Hermite插值神经网络具有更好的收敛速度和校验能力。同时,也验证了该神经网络良好的降噪和预测能力。

ADAPTIVE PREDICTIVE CONTROL OF NEAR-SPACE VEHICLE USING FUNCTIONAL LINK NETWORK

A novel nonlinear adaptive control method is presented for a near-space hypersonic vehicle （NHV） in the presence of strong uncertainties and disturbances. The control law consists of the optimal generalized predictive controller （OGPC） and the functional link network （FLN） direct adaptive law. OGPC is a continuous-time nonlinear predictive control law. The FLN adaptive law is used to offset the unknown uncertainties and disturbances in a flight through the online learning. The learning process does not need any offline training phase. The stability analyses of the NHV close-loop system are provided and it is proved that the system error and the weight learning error are uniformly ultimately hounded. Simulation results show the satisfactory performance of the con- troller for the attitude tracking.

Robust adaptive dynamic surface control for nonlinear uncertain systems

We propose a new method for robust adaptive backstepping control of nonlinear systems with parametric uncertainties and disturbances in the strict feedback form. The method is called dynamic surface control. Traditional backstepping algorithms require repeated differentiations of the modelled nonlinearities. The addition of n first order low pass filters allows the algorithm to be implemented without differentiating any model nonlinearities, thus ending the complexity arising due to the 'explosion of terms' that makes other methods difficult to implement in practice. The combined robust adaptive backstepping/first order filter system is proved to be semiglobally asymptotically stable for sufficiently fast filters by a singular perturbation approach. The simulation results demonstrate the feasibility and effectiveness of the controller designed by the method.

Decentralized H_∞ state feedback control for large-scale interconnected uncertain systems with multiple delays

Decentralized H_∞ control was studied for a class of interconnected uncertain systems with multiple delays in the state and control and time varying but norm-bounded parametric uncertainties. A sufficient condition which makes the closed-loop system decentralized asymptotically stable with H_∞ performance was derived based on Lyapunov stability theorem. This condition is expressed as the solvability problem of linear matrix inequalities. The method overcomes the limitations of the existing algebraic Riccati equation method. Finally, a numerical example was given to demonstrate the design procedure for the decentralized H_∞ state feedback controller.

Guaranteed Cost Control for Uncertain Nonlinear Time-Delay Neutral Systems Based on T-S Fuzzy Model

The problem of guaranteed cost fuzzy controller is studied for a class of nonlinear time-delay neutral sys-tems with norm-bounded uncertainty based on T-S model. The sufficient conditions are first derived for the existenceof guaranteed cost fuzzy controllers. These sufficient conditions are equivalent to a kind of linear matrix inequalities.Furthermore, a convex optimization problem with LMI constraints is formulated to design the optimal guaranteedcost controller.

Autonomous determination of orbit for probe around asteroids using unscented Kalman filter

The observed images of the asteroid and the asteroid reference images are used to obtain the probe-to-asteroid direction and the location of the limb features of the asteroid in the inertial coordinate. These informa-tion in combination with the shape model of the asteroid and attitude information of the probe are utilized to ob-tain the position of the probe. The position information is then input to the UKF which determines the real-timeorbit of the probe. Finally, the autonomous orbit determination algorithm is validated using digital simulation.The determination of orbit using UKF is compared with that using extended Kalman filter (EKF), and the resultshows that UKF is superior to EKF.

A New Tuning Method for Two-Degree-of-Freedom Internal Model Control under Parametric Uncertainty

Internal model control （IMC） yields very good performance for set point tracking, but gives sluggish response for disturbance rejection problem. A two-degree-of-freedom IMC （2DOF-IMC） has been developed to overcome the weakness. However, the setting of parameter becomes a complicated matter if there is an uncertainty model. The present study proposes a new tuning method for the controller. The proposed tuning method consists of three steps. Firstly, the worst case of the model uncertainty is determined. Secondly, the parameter of set point con- troller using maximum peak （Mp） criteria is specified, and finally, the parameter of the disturbance rejection con- troller using gain margin （GM） criteria is obtained. The proposed method is denoted as Mp-GM tuning method. The effectiveness of Mp-GM tuning method has evaluated and compared with IMC-controller tuning program （IMCTUNE） as bench mark. The evaluation and comparison have been done through the simulation on a number of first order plus dead time （FOPDT） and higher order processes. The FOPDT process tested includes processes with controllability ratio in the range 0.7 to 2.5. The higher processes include second order with underdarnped and third order with nonminimum phase processes. Although the two of higher order processes are considered as difficult processes, the proposed Mp-GM tuning method are able to obtain the good controller parameter even under process uncertainties.

Mothers overcoming remorse to care for self and baby:An emerging concept

Objectives:Mothers with substance use disorder(SUD)experience a range of emotions such as feeling ostracized,diminished,and distressed while watching their baby experience withdrawal from substances.Being fully present in the now moment is to trust self to do what is best by moving beyond perceived boundaries to care for self and baby.The process of concept building arose from nursing practice encounters in a special care nursery(SCN)for babies who experienced withdrawal from substances.Method:Liehr and Smith’s 10-phase concept building approach was used to guide the development of this concept.Concept building began with a practice story.The emerging concept was named,core qualities identified,and supported through a literature review.The middle range theory of uncertainty in illness was chosen to serve as theoretical support for the concept.A model was created to provide clarity on the relationships within the concept.Result:A mini-saga was gathered from a mother in the SCN whose newborn had experienced withdrawal from substances.The minisaga follows:Due to the baby’s discomfort and judging eyes of the staff,she was unable to mother her baby.As the baby recovered,she asked for help,comforted her baby,and gained confidence to move beyond perceived boundaries to become the mother she envisioned.Overcoming perceived boundaries to attend to self and baby is trusting oneself to do what is best in spite of feeling ostracized,diminished,and distressed while watching baby withdraw from substances.Conclusion:This concept provides the perspective of mothers with SUD through intermodernism from experiences in nursing practice.The Uncertainty in Illness theory further allows practitioners to gain an understanding of the role uncertainty plays in this unique situation.

A Self-Adaptive Control Method for Uncertainty Systems Based on ANN with AEP

A self-adaptive control method is proposed based on an artificial neural network(ANN)with accelerated evolutionary programming(AEP)algorithm.The neural network is used to model the uncertainty process,from which the teacher signals are produced online to regulate the parameters of the controller.The accelerated evolutionary programming is used to train the neural network.The experiment results show that the method can obviously improve the dynamic performance of uncertainty systems.

Adaptive control using interval Type-2 fuzzy logic for uncertain nonlinear systems

A new adaptive Type-2 （T2） fuzzy controller was developed and its potential performance advantage over adaptive Type-1 （T1） fuzzy control was also quantified in computer simulation. Base on the Lyapunov method, the adaptive laws with guaranteed system stability and convergence were developed. The controller updates its parameters online using the laws to control a system and tracks its output command trajectory. The simulation study involving the popular inverted pendulum control problem shows theoretically predicted system stability and good tracking performance. And the comparison simulation experiments subjected to white noige or step disturbance indicate that the T2 controller is better than the T1 controller by 0--18%, depending on the experiment condition and performance measure.

Fabrication of automatic switch for AC-DC completely automated measurement system at NIS

A fast automatic AC-DC switch is designed and fabricated mainly by a microcontroller and three double poles single throw reed relays.This new switch is introduced to establish a fully automated system for AC-DC measurements through ACDC transfer standards for the first time at the National Institute for standards(N IS)in Egypt.The implemented circuit of theautomatic AC-DC switch and its protection are presented in details.An AC voltage source is calibrated against DC voltagesource by using the demonstrated automatic switch as an application The calibrated voltage ranges are2V,6V,20V and60V as examples.The uncertainty budget is also evaluated for the calibrated values.

Adaptive backstepping control for levitation system with load uncertainties and external disturbances

To explore the precise dynamic response of the levitation system with active controller, a maglev guide way-electromagnet-air spring-cabin coupled model is derived firstly. Based on the mathematical model, it shows that the inherent nonlinearity, inner coupling, misalignments between the sensors and actuators, load uncertainties and external disturbances are the main issues that should be solved in engineering. Under the assumptions that the loads and external disturbance are measurable, the backstepping module controller developed in this work can tackle the above problems effectively. In reality, the load is uncertain due to the additions of luggage and passengers, which will degrade the dynamic performance. A load estimation algorithm is introduced to track the actual load asymptotically and eliminate its influence by tuning the parameters of controller online. Furthermore,considering the external disturbances generated by crosswind, pulling motor and air springs, the extended state observer is employed to estimate and suppress the external disturbance. Finally, results of numerical simulations illustrating closed-loop performance are provided.

Gait Recorded by Smart Phone Can Reveal Your Emotion

So far,a lot of scientific studies have been carried out on nonverbal signals,which are considered as extrinsic expression of human’s intrapsychic state.Among them,emotion detection aims to automatically determine a person’s affective state,with immense potentials in many areas from health care,psychological detection to human-computer interaction.Traditional emotion detection is based on expressions,or linguistic and acoustic features in speech.However,

Uncertainty Calculation of Roundness Assessment by Automatic Differentiation in Coordinate Metrology

Reomtly, Coordinate bieasuring Machines （CMMs） are widely used to measure roundness errors. Roundness is calculated from a large number of points collected from the profiles of the parts. According to the Guide to the Expression of Uncertainty in Measta- meat （GUM）, all measurement results must have a stated uncertainty associated the titan. However, no CMMs give the uncertainty value of the roundness, because no suitable measrement uncertainty calculation procedure exists. In the case of roundness raeasurement in coordinate metrology, this paper suggests the algorithms for the calculation of the measurement uncertainty of the roudness deviation based on the two mainly used association criteria, LSC and MZC. The calculation of the sensitivity coefficients for the uncertainty calculatiion can be done by autnatic differentiation, in order to avoid introducing additional emars by the traditional difference quotient approxima- tions. The proposed methods are exact and need input data only as the nrasured coordinates of the data points and their associated un- certainties.

The Narrative Perspectives Manifested in AI-Kharrat＇s Novels

This study deals with two novels of Eduar AI-Kharrat： Rama wal-Tinnin （Rama and the Dragon, 1979） and al-Zaman al-Akhar （The Other Time, 1985）. The text in both novels is of the pluralist, polyphonic and modernistic type and the real and the imaginary are juxtaposed. The narrative imitates at its diverse levels the internal conflict, argument, and uncertainty of the protagonist Michael, who finally finds his self-realization in an imaginary time, ＂the other time＂, which is also the title of one of the novels. The present study focuses on the transformation and alternation of the perspectives and the narrative vision through the destruction of the narrator＇s identity and the text itself, the analysis of the narrative shift between the first and third person, the fragmentation of the self, the ambiguity of the signs, the severity of the crisis, and the psychological conflict at its diverse levels and multiplicities. Toward this plurality and shift, it is necessary to systematically depend upon what the theories of Bakhtin and Genette have to offer in order to cover the narrative levels and multiple voices prevailing in the texts.

Actuator fault diagnosis of autonomous underwater vehicle based on improved Elman neural network

Autonomous underwater vehicles(AUV) work in a complex marine environment. Its system reliability and autonomous fault diagnosis are particularly important and can provide the basis for underwater vehicles to take corresponding security policy in a failure. Aiming at the characteristics of the underwater vehicle which has uncertain system and modeling difficulty, an improved Elman neural network is introduced which is applied to the underwater vehicle motion modeling. Through designing self-feedback connection with fixed gain in the unit connection as well as increasing the feedback of the output layer node, improved Elman network has faster convergence speed and generalization ability. This method for high-order nonlinear system has stronger identification ability. Firstly, the residual is calculated by comparing the output of the underwater vehicle model(estimation in the motion state) with the actual measured values. Secondly, characteristics of the residual are analyzed on the basis of fault judging criteria. Finally, actuator fault diagnosis of the autonomous underwater vehicle is carried out. The results of the simulation experiment show that the method is effective.

Method of measuring rotation speed of high spinning projectile based on plane magnetic induction coil

For the test of rotation speed of high spinning projectile, the general formula of the motional electromotive force （MEMF） of planar magnetic induction coil （PMIC） is derived in case of 3D rotation in a stable magnetic field. Under a reasona-ble assumption, the MEMF of PMIC is simplified after the aforementioned general formula is used to calculate high spinning PMIC in the geomagnetic field environment. The determination approach of half-cycle is discussed and the method of rotation speed test is studied, and a test is conducted in the paper. The rotation speed curve obtained by the approach in this paper is consistent with the curve by telemetry.