Inverse technique identification of material parameters using finite element and neural network computation

Experimental identification of anisotropic behavior law is currently obtained by performing several complicated tests and a long duration of experiments. This paper describes a new technique allowing for the identification of HILL anisotropic parameters by inverse technique method based on deep drawing of a cylindrical cup. The identification approach is based on the artificial neural network (ANN) computation trained from finite element simulation. The results obtained by ANN models and by the finite element method shows a good agreement.     

风杯风速计测风误差的分析研究与订正方法

本文利用内蒙古科尔沁沙地开展的大气边界层实验资料。对比分析了美国Teledyne公司专为微气象学精细结构研究生产的M50．1B型轻型低阈值风杯风速计和长春气象仪器研究所生产的EC9-1型风杯风速计的误差和订正方法。结果表明：两种风杯风速仪各自水平比较实验结果都具有较好的一致性；美国风杯风速计偏离其平均值的百分比与风速有较为显著的负相关关系。通过对M50．1B型风杯风速计与超声风速仪的对比观测．本文还计算并讨论了M50．1B型轻型低阈值风杯风速计的误差大小和可能的误差来源，发现DP误差所占的比例较低，而U误差和其它因素对该风杯风速计测风有较强的影响。     

On cup anemometer performance at high altitude above ground

In this paper, an experimental wind tunnel test campaign to assess the possibility of using cup anemometers at high altitude (~20 km) is performed. The experimental procedure consists of measuring the evolution of the rotational frequency for different wind dynamic pressures for different cups and the center of rotation radius. With particular interest on the point at which the rotation stops for decreasing values of the dynamic pressure is considered as the limit value for the anemometer operation. The results show that large cup radius anemometer rotors present more stable behavior (its stopping point at low wind speeds being less affected by the cups’ center rotation radius). The authors conclude that cup anemometers can be used at high altitude above ground. Results show that an anemometer equipped with a 40 mm cup radius rotor could be considered operative up to an altitude of 25 km above ground.     

传感器动态补偿的神经网络逆系统方法

给出一种基于神经网络逆系统的传感器动态补偿策略。无需传感器具体模型和参数，即可实现传感器系统的近似单位线性化，达到动态补偿的目的。仿真实验和动态标定试验结果表明，应用这种新型的易于工程实现的动态补偿方法可显著地提高传感器的动态特性，有效改善传感器的动态品质。     

Prediction of calcium concentration in human blood serum using an artificial neural network

A predictive method, based on artificial neural network (ANN) has been developed to study absorbance and pH effects on the equilibrium of blood serum. This strategy has been used to analyze serum samples and to predict the calcium concentration in blood serum. A dedicated data acquisition system is designed and fabricated using a LPC2106 microcontroller with light emitting diode (LED) as source and photodiode as sensor to measure absorbance and to calculate the calcium concentration. A multilayer neural network with back propagation (BP) training algorithm is used to simulate different concentration of calcium (Ca²⁺) as a function of absorbance and pH, to correlate and predict calcium concentration. The computed calcium concentration by neural network is quite satisfactory with correlations R² = 0.998 and 0.995, standard errors of 0.0127 and 0.0122 in validation and testing stages respectively. Statistical analysis are carried out to check the accuracy and precision of the proposed ANN model and validation of results produce a relative error of about 3%. These results suggest that ANN can be efficiently applied and is in good agreement with values obtained with the current clinical spectrophotometric methods. Hence, ANN can be used as a complementary tool for studying metal ion complexion, with special attention to the blood serum analysis.     

Physics-based recalibration method of cup anemometers

Cup anemometer is the most widely used instrument in the natural environment. However, the accuracy of cup anemometer is not robust due to their inertial structures. In this study, the equation of motion (EOM) relating rotational motion of the cup rotor to aerodynamic force is investigated to reveal the cause of measurement error of cup anemometer. A new methodology is proposed to recalibrate cup anemometer based on theoretical analysis of the dynamic response of the cup rotor and random process theory. The unknown dynamic coefficients of the EOM are quantified by the numerical method using measurement results from inertial and non-inertial anemometers. A detailed example is presented to demonstrate the efficiency of this new method in which coefficients of the EOM are quantified from laboratory and field data. Both mean wind speed and the entire time history could be recalibrated using this new method. Comparing with the non-inertial anemometer results, the improvement rate of the recalibrated cup anemometer results is 29%–99%.     

Application of a neural network to predict thickness strains and finite element simulation of hydro-mechanical deep drawing

In this paper an artificial neural network (ANN) is used to predict the thickness along a cup wall in hydro-mechanical deep drawing. This model uses a feed-forward back-prorogation neural network. After using the experimental results to train and test the network, the model was applied to new data for the prediction of thickness strains in hydro-mechanical deep drawing. The results are promising. In the present work, we also attempt to perform a finite element simulation of the process for the two dimensional axi-symmetric case using explicit finite element code LS-DYNA 2D. Counter pressure on the blank is applied by specifying the pressure boundary conditions. A comparison was made between simulated, experimental and ANN results of hydro-mechanical deep drawing using low carbon extra deep drawing grade steel sheets of 0.96 mm thickness. It was also found that by hydro-mechanical deep drawing, a higher drawability and a more uniform thickness distribution were obtained when compared to conventional deep drawing.     

无轴承永磁同步电机的神经网络逆控制

无轴承永磁同步电机是一个强耦合的非线性复杂系统,实现无轴承永磁同步电机的线性化解耦控制,是无轴承永磁同步电机稳定运行和走向实用化的关键。将神经网络具有的特点（对非线性系统的逼近能力以及对系统参数变化的适应能力）与逆系统方法的特点（解耦线性化）相结合,提出了基于神经网络的无轴承永磁同步电机逆系统解耦控制方法。通过用静态神经网络加积分器来构造无轴承永磁同步电机的逆系统,将无轴承永磁同步电机动态解耦成位移子系统和转速子系统分别设计调节器进行控制,然后运用线性系统理论进行综合。仿真及实验结果表明,系统具有良好的鲁棒性和动静态解耦性能。

     

复杂曲面车削精度的神经网络控制

提出了一种基于神经网络的加工误差控制方法，引入神经网络对加工系统的逆模型进行辩识，运用该模型前置校正加工系统以改善加工精度。该方法在中凸变椭圆活塞裙面加工中的成功应用，证明了其合理性及先进性。     

The experimental identification of magnetorheological dampers and evaluation of their controllers

Magnetorheological (MR) fluid dampers are semi-active control devices that have been applied over a wide range of practical vibration control applications. This paper concerns the experimental identification of the dynamic behaviour of an MR damper and the use of the identified parameters in the control of such a damper. Feed-forward and recurrent neural networks are used to model both the direct and inverse dynamics of the damper. Training and validation of the proposed neural networks are achieved by using the data generated through dynamic tests with the damper mounted on a tensile testing machine. The validation test results clearly show that the proposed neural networks can reliably represent both the direct and inverse dynamic behaviours of an MR damper. The effect of the cylinder's surface temperature on both the direct and inverse dynamics of the damper is studied, and the neural network model is shown to be reasonably robust against significant temperature variation. The inverse recurrent neural network model is introduced as a damper controller and experimentally evaluated against alternative controllers proposed in the literature. The results reveal that the neural-based damper controller offers superior damper control. This observation and the added advantages of low-power requirement, extended service life of the damper and the minimal use of sensors, indicate that a neural-based damper controller potentially offers the most cost-effective vibration control solution among the controllers investigated.     

Application of neural network technique to high energy milling process for synthesizing ZnO nanopowders

An artificial-neural-network (ANN) model was developed to estimate the crystalline size of ZnO nanopowder as a function on the milling parameters such as milling times and balls to powder ratio. This nanopowder was synthesized by high energy mechanical milling and the required data for training were collected from the experimental results. The synthesized ZnO nanoparticles are characterized by X-ray diffraction (XRD) and scanning electron microcopy (SEM). It was found that artificial neural network was very effective providing a perfect agreement between the outcomes of ANN modeling and experimental results with an error by far better than multiple linear regressions. An optimization model and this experimental validation of the ball milling process for producing the nanopowder ZnO are carried out.     

Hybrid FE/ANN and LPR approach for the inverse identification of material parameters from cutting tests

Accuracy of numerical models based in finite elements (FE), extensively used for simulation of cutting processes, depends strongly on the identification of proper material parameters. Experimental identification of the constitutive law parameters for simulation of cutting processes involves unsolved problems such as the complex testing techniques or the difficulty to reproduce the stress triaxiality state during cutting. This work proposes a methodology for the inverse identification of the material parameters from cutting test. Two hybrid approaches are compared. One of them based on FE and artificial neural networks (ANN). The other one based on FE and local polynomial regression (LPR). Firstly, a FE model is validated with experimental data. Then, ANN and LPR are trained with FE simulations. Finally, the estimated ANN and LPR models are used for the inverse identification of material parameters. This identification is solved as an optimization problem. The FE/LPR approach shows good performance, outperforming the FE/ANN approach.     

Practical applications of artificial neural networks in chemical process development

Artificial neural networks (ANN) have the ability to map non-linear relationships without a-priori information about process or system models. This significant feature allows the network to “learn” the behavior of a system by example when it may be difficult or impractical to complete a rigorous mathematical solution. Recently ANN technology has been leaving the academic arena and placed in user-friendly software packages. This paper will offer an introduction to artificial neural networks and present a case history of two problems in chemical process development that were approached with ANN. Both optimal PID control tuning parameters and product particle size predictions were constructed from process information using neural networks. The ANN provides a rapid solution to many applications with little physical insight into the underlying system function. The amount of data preparation and performance limitations using a neural network will be discussed. However, the properly applied ANN will generally provide insight to which variables are most influential to the model and evolve dynamically to the minimum performance surface squared error. Neural networks have been used successfully with non-linear dynamic systems and can be applied to chemical process development for system identification and multivariate optimization problems.     

Optimum surface roughness prediction in face milling by using neural network and harmony search algorithm

This paper presents a new approach to determine the optimal cutting parameters leading to minimum surface roughness in face milling of X20Cr13 stainless steel by coupling artificial neural network (ANN) and harmony search algorithm (HS). In this regard, advantages of statistical experimental design technique, experimental measurements, analysis of variance, artificial neural network and harmony search algorithm were exploited in an integrated manner. To this end, numerous experiments on X20Cr13 stainless steel were conducted to obtain surface roughness values. A predictive model for surface roughness was created using a feed forward neural network exploiting experimental data. The optimization problem was solved by harmony search algorithm. Additional experiments were performed to validate optimum surface roughness value predicted by HS algorithm. The obtained results show that the harmony search algorithm coupled with feed forward neural network is an efficient and accurate method in approaching the global minimum of surface roughness in face milling.     

基于神经网络的复杂曲面加工误差控制

在复杂曲面的切削过程中，加工系统表现显著的多输入多输出及非线性特征，传统的误差补偿方法不能有效地保证加工精度，因此提出一种加工误差控制方法，引入神经网络对加工系统的逆模型进行辨识，运用该模型前置校正加工系统以改善加工效果，充分考虑到机械系统的非线性特征，且网络模型可连续辨识，因而系统的静态性能和动态特性均能有效补偿，在中凸变椭圆活塞裙面加工中的成功应用，证明其合理性及先进性。     

Prediction of contraction scour using ANN and GA

This paper emphasizes on the application of soft computing tools such as artificial neural network (ANN) and genetic algorithm (GA) in the prediction of scour depth within channel contractions. The experimental data of earlier investigators are used in developing the models and ANN and GA Toolboxes of MATLAB software are utilized for the purpose. The multilayered perceptron (MLP) neural networks with feed-forward back-propagation training algorithms were designed to predict the scour depth. The mean squared error and correlation coefficient are used to check the performance of networks. It is found that the ANN architecture 4-16-1 having trained with Levenberg-Marquardt ‘trainlm’ function had best performance having mean squared error of 0.001 and correlation coefficient of 0.998. In addition, the suitability of ‘trainlm’ method over other training methods is also discussed. The scour depths predicted by ANN model were compared with those computed by the two analytical models (with and without sidewall correction for contracted zone) and an empirical model proposed by Dey and Raikar [1]. In addition, heuristic search technique called genetic algorithm is used to develop the predictor for maximum scour depth within channel contraction. The population size for GA was 500 members with total generations of 1000, crossover fraction of 0.8 and Gaussian operator for mutation. It is promising to observe that the GA model predicts the maximum scour depth equally well as that of empirical model of Dey and Raikar [1]. Hence, both ANN and GA models can be satisfactorily used to predict the scour depth within channel contractions.     

风杯式风速传感器启动风速校准实验箱的分析与设计

针对风杯式风速传感器启动风速现场实时校准问题,分析了影响风杯式风速传感器启动风速的因素,提出了现场测量启动风速的方法,基于此方法设计了启动风速校准实验箱,为获得最优实验箱结构参数,通过Fluent软件分别研究了不同结构的动力段、整流段以及收缩段对实验箱流场形态的影响,选取合适的结构,确定了实验箱结构在不同风扇转速下的流场形态,结果表明:所设计的实验箱出口段气流速度平稳,方向一致,满足校准需求。     

An alternative mathematical model of vane anemometers based on the balance of power

Anemometers based on the exchange of momentum between the flow and rotating measuring element comprise an important class of instruments used in flow metrology, especially in meteorological and ventilation measurements. In these instruments, overvaluation of the measured average velocity, caused by the inertia of their rotors, takes place. To analyse this phenomenon and the dynamics of the measurement process, as well as to estimate and minimize the measurement uncertainty, it is required to be acquainted with the mathematical model of the anemometer. In this study, the model of the vane anemometer based on the equation of motion of its rotor available in the literature is analysed, and a new model based on the power balance is proposed. Model testing and a comparison of both models has also been performed.     

Application of a flexible structure artificial neural network on a servo-hydraulic rotary actuator

In this article the results of the application of a flexible structure artificial neural network for controlling the angular velocity of a servo-hydraulic rotary actuator are discussed. A mathematical model for the system is derived, and a flexible artificial neural network (ANN)-based controller with the feedback error learning method as a learning algorithm is applied to the system. The neural network-based controller has a feed-forward structure and three layers. The flexible bipolar sigmoid function was used as the activation function of the network. The simulation and experimental results show good performance of the developed method in learning the inverse dynamic of the system and controlling the angular velocity of the rotary hydro motor. The advantages of the developed method for servo-hydraulic actuators over other traditional approaches are discussed.     

On the FSW of AA2024-T4 and AA7075-T6 T-joints: an industrial case study

The paper presents an artificial neural network-optimization hybrid model to predict and optimize penetration depth of CO₂ LASER-MIG hybrid welding used for 5005 Al–Mg alloy. The input welding parameters are power, focal distance from the work piece surface, torch angle, and the distance between the laser and the welding torch. The model combines single hidden layer back propagation artificial neural networks (ANN) with Bayesian regularization for prediction and quasi-Newton search algorithm for optimization. In this method, training and prediction performance of different ANN architectures are initially tested, and the architecture with the best performance is further used for optimization. Finally, the best ANN architecture is found to show much better prediction capability compared to a regression model developed from the experimental data.