人工神经网络在医用多元分析中的应用

作者将人工神经网络的一典型模型——“反向传播”模型应用到医用的多元分析中。所选实例的研究结果表明,该方法性能良好,可望成为医用多元分析的一种有效手段。

人工神经网络用于煤直接液化反应模拟的研究

采用人工神经网络的方法模拟了煤直接液化过程中各变量之间的非线性关系。选用ｌｅａｖｅｏｎｅｏｕｔ 的交叉验证（ｃｒｏｓｓｖａｌｉｄａｔｉｏｎ） 方法确定网络的最佳拓扑结构， 达到对催化条件下煤直接液化过程最大限度的拟合。结果表明， 尽管部分样本的预报绝对误差大于１０ ％ ， 人工神经网络可以较好地模拟反应条件与产物产率之间的关系， 并能准确预报催化剂浸渍量对煤的总转化率和沥青烯轻质产物产率的影响趋势。由于实验数据的分散性较大， 以及网络自身结构参数的沉余， 使得人工神经网络对部分煤液化实验数据拟合时出现过拟合现象。因此，提高实验数据的可靠性， 结合经典动力学模型描述反应过程的物理特征是必要的。

Prediction of Hot Deformation Behavior of 7Mo Super Austenitic Stainless Steel Based on Back Propagation Neural Network

The hot compression tests of 7Mo super austenitic stainless(SASS)were conducted to obtain flow curves at the temperature of 1000-1200℃and strain rate of 0.001 s^(-1)to 1 s^(-1).To predict the non-linear hot deformation behaviors of the steel,back propagation-artificial neural network(BP-ANN)with 16×8×8 hidden layer neurons was proposed.The predictability of the ANN model is evaluated according to the distribution of mean absolute error(MAE)and relative error.The relative error of 85%data for the BP-ANN model is among±5%while only 42.5%data predicted by the Arrhenius constitutive equation is in this range.Especially,at high strain rate and low temperature,the MAE of the ANN model is 2.49%,which has decreases for 18.78%,compared with conventional Arrhenius constitutive equation.

Simultaneous Identification of Thermophysical Properties of Semitransparent Media Using a Hybrid Model Based on Artificial Neural Network and Evolutionary Algorithm

A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.

Prediction of mechanical properties of A357 alloy using artificial neural network

The workpieces of A357 alloy were routinely heat treated to the T6 state in order to gain an adequate mechanical property.The mechanical properties of these workpieces depend mainly on solid-solution temperature,solid-solution time,artificial aging temperature and artificial aging time.An artificial neural network（ANN） model with a back-propagation（BP） algorithm was used to predict mechanical properties of A357 alloy,and the effects of heat treatment processes on mechanical behavior of this alloy were studied.The results show that this BP model is able to predict the mechanical properties with a high accuracy.This model was used to reflect the influence of heat treatments on the mechanical properties of A357 alloy.Isograms of ultimate tensile strength and elongation were drawn in the same picture,which are very helpful to understand the relationship among aging parameters,ultimate tensile strength and elongation.

Constructing processing map of Ti40 alloy using artificial neural network

Based on the experimental data of Ti40 alloy obtained from Gleeble-1500 thermal simulator,an artificial neural network model of high temperature flow stress as a function of strain,strain rate and temperature was established.In the network model,the input parameters of the model are strain,logarithm strain rate and temperature while flow stress is the output parameter.Multilayer perceptron（MLP） architecture with back-propagation algorithm is utilized.The present study achieves a good performance of the artificial neural network（ANN） model,and the predicted results are in agreement with experimental values.A processing map of Ti40 alloy is obtained with the flow stress predicted by the trained neural network model.The processing map developed by ANN model can efficiently track dynamic recrystallization and flow localization regions of Ti40 alloy during deforming.Subsequently,the safe and instable domains of hot working of Ti40 alloy are identified and validated through microstructural investigations.

Recovery of indium by acid leaching waste ITO target based on neural network

The optimized leaching techniques were studied by technical experiment and neural network optimization for improving indium leaching rate. Firstly, effect of single technical parameter on leaching rate was investigated experimentally with other parameters fixed as constants. The results show that increasing residual acidity can improve leaching rate of indium. Increasing the oxidant content can obviously increase leaching rate but the further addition of oxidant could not improve the leaching rate. The enhancement of temperature can improve the leaching rate while the further enhancement of temperature decreases it. Extension leaching time can improve the leaching rate. On this basis, a BPNN model was established to study the effects of multi-parameters on leaching rate. The results show that the relative error is extremely small, thus the BPNN model has a high prediction precision. At last, optimized technical parameters which can yield high leaching rate of 99.5%were obtained by experimental and BPNN studies：residual acidity 50-60 g/L, oxidant addition content 10%, leaching temperature 70 ℃ and leaching time 2 h.

Optimum design of flow distribution in quenching tank for heat treatment of A357 aluminum alloy large complicated thin-wall workpieces by CFD simulation and ANN approach

Based on the computational fluid dynamics （CFD） method, a quenching tank with two agitator systems and two flow-equilibrating devices was selected to simulate flow distribution using Fluent software. A numerical example was used to testify the validity of the quenching tank model. In order to take tank parameters （agitation speed, position of directional flow baffle and coordinate position in quench zone） into account, an approach that combines the artificial neural network （ANN） with CFD method was developed to study the flow distribution in the quenching tank. The flow rate of the quenching medium shows a very good agreement between the ANN predicted results and the Fluent simulated data. Methods for the optimal design of the quenching tank can be used as technical support for industrial production.

PC-based artif icial neural network inversion for airborne time-domain electromagnetic data

Traditionally, airborne time-domain electromagnetic （ATEM） data are inverted to derive the earth model by iteration. However, the data are often highly correlated among channels and consequently cause ill-posed and over-determined problems in the inversion. The correlation complicates the mapping relation between the ATEM data and the earth parameters and thus increases the inversion complexity. To obviate this, we adopt principal component analysis to transform ATEM data into orthogonal principal components （PCs） to reduce the correlations and the data dimensionality and simultaneously suppress the unrelated noise. In this paper, we use an artificial neural network （ANN） to approach the PCs mapping relation with the earth model parameters, avoiding the calculation of Jacobian derivatives. The PC-based ANN algorithm is applied to synthetic data for layered models compared with data-based ANN for airborne time-domain electromagnetic inversion. The results demonstrate the PC-based ANN advantages of simpler network structure, less training steps, and better inversion results over data-based ANN, especially for contaminated data. Furthermore, the PC-based ANN algorithm effectiveness is examined by the inversion of the pseudo 2D model and comparison with data-based ANN and Zhody＇s methods. The results indicate that PC-based ANN inversion can achieve a better agreement with the true model and also proved that PC-based ANN is feasible to invert large ATEM datasets.

Improvement and application of neural network models in development of wrought magnesium alloys

Neural network models of mechanical properties prediction for wrought magnesium alloys were improved by using more reasonable parameters, and were used to develop new types of magnesium alloys. The parameters were confirmed by comparing prediction errors and correlation coefficients of models, which have been built with all the parameters used commonly with training of all permutations and combinations. The application was focused on Mg-Zn-Mn and Mg-Zn-Y-Zr alloys. The prediction of mechanical properties of Mg-Zn-Mn alloys and the effects of mole ratios of Y to Zn on the strengths in Mg-Zn-Y-Zr alloys were investigated by using the improved models. The predicted results are good agreement with the experimental values. A high strength extruded Mg-Zn-Zr-Y alloy was also developed by the models. The applications of the models indicate that the improved models can be used to develop new types of wrought magnesium alloys.

Springback prediction for incremental sheet forming based on FEM-PSONN technology

In the incremental sheet forming （ISF） process, springback is a very important factor that affects the quality of parts. Predicting and controlling springback accurately is essential for the design of the toolpath for ISF. A three-dimensional elasto-plastic finite element model （FEM） was developed to simulate the process and the simulated results were compared with those from the experiment. The springback angle was found to be in accordance with the experimental result, proving the FEM to be effective. A coupled artificial neural networks （ANN） and finite element method technique was developed to simulate and predict springback responses to changes in the processing parameters. A particle swarm optimization （PSO） algorithm was used to optimize the weights and thresholds of the neural network model. The neural network was trained using available FEM simulation data. The results showed that a more accurate prediction of s!oringback can be acquired using the FEM-PSONN model.

Hot deformation behavior and processing maps of Mg-Zn-Cu-Zr magnesium alloy

The deformation behaviors of a new quaternary Mg-6Zn-1.5Cu-0.5Zr alloy at temperatures of 523-673 K and strain rates of 0.001-1 s-1 were studied by compressive tests using a Gleeble 3800 thermal-simulator.The results show that the flow stress increases as the deformation temperature decreases or as the strain rate increases.A strain-dependent constitutive equation and a feed-forward back-propagation artificial neural network were used to predict flow stress,which showed good agreement with experimental data.The processing map suggests that the domains of 643-673 K and 0.001-0.01 s-1 are corresponded to optimum conditions for hot working of the T4-treated Mg-6Zn-1.5Cu-0.5Zr alloy.

Application of novel physical picture based on artificial neural networks to predict microstructure evolution of Al-Zn-Mg-Cu alloy during solid solution process

The effects of the solid solution conditions on the microstructure and tensile properties of Al?Zn?Mg?Cu aluminum alloy were investigated by in-situ resistivity measurement, optical microscopy (OM), scanning electron microscopy (SEM), transmission electron microscopy (TEM) and tensile test. A radial basis function artificial neural network (RBF-ANN) model was developed for the analysis and prediction of the electrical resistivity of the tested alloy during the solid solution process. The results show that the model is capable of predicting the electrical resistivity with remarkable success. The correlation coefficient between the predicted results and experimental data is 0.9958 and the relative error is 0.33%. The predicted data were adopted to construct a novel physical picture which was defined as “solution resistivity map”. As revealed by the map, the optimum domain for the solid solution of the tested alloy is in the temperature range of 465?475 °C and solution time range of 50?60 min. In this domain, the solution of second particles and the recrystallization phenomenon will reach equilibrium.

Compositional optimization of glass forming alloys based on critical dimension by using artificial neural network

An artificial neural network （ANN） model was developed for simulating and predicting critical dimension dc of glass forming alloys. A group of Zr-Al-Ni-Cu and Cu-Zr-Ti-Ni bulk metallic glasses were designed based on the dc and their de values were predicted by the ANN model. Zr-Al-Ni-Cu and Cu-Zr-Ti-Ni bulk metallic glasses were prepared by injecting into copper mold. The amorphous structures and the determination of the dc of as-cast alloys were ascertained using X-ray diffraction. The results show that the predicted de values of glass forming alloys are in agreement with the corresponding experimental values. Thus the developed ANN model is reliable and adequate for designing the composition and predicting the de of glass forming alloy.

Integrated assessment of sea water quality based on BP artificial neural network

In order to carry out an integrated assessment of sea water quality objectively, this paper based on the concept and principle of artificial neural network, generated appropriate training samples for BP artificial neural network model through the method of producing samples to the concentration of various pollution index of sea water quality from the viewpoint of threshold, established the BP artificial neural network model of sea water quality assessment using multi-layer neural network with error back-propagation algorithm. This model was used to assess water environment and obtain sea water quality categories of offshore area in Bohai Bay through calculating. The calculations shown that pollution index in river＇s wet season was higher than that in dry season from 2004 to 2007, and the pollution was particularly serious in 2005 and 2006, but a little better in 2007. The assessed results of cases shown that the model was reasonable in design and higher in generalization, meanwhile, it was common, objective and practical to sea water quality assessment.

Combining the genetic algorithms with artificial neural networks for optimization of board allocating

This paper introduced the Genetic Algorithms (GAs) and Artificial Neural Networks (ANNs), which have been widely used in optimization of allocating. The combination way of the two optimizing algorithms was used in board allocating of furniture production. In the experiment, the rectangular flake board of 3650 mm 1850 mm was used as raw material to allocate 100 sets of Table Bucked. The utilizing rate of the board reached 94.14 % and the calculating time was only 35 s. The experiment result proofed that the method by using the GA for optimizing the weights of the ANN can raise the utilizing rate of the board and can shorten the time of the design. At the same time, this method can simultaneously searched in many directions, thus greatly in-creasing the probability of finding a global optimum.

Real-Time Face Tracking and Recognition in Video Sequence

A framework of real time face tracking and recognition is presented, which integrates skin color based tracking and PCA/BPNN (principle component analysis/back propagation neural network) hybrid recognition techniques. The algorithm is able to track the human face against a complex background and also works well when temporary occlusion occurs. We also obtain a very high recognition rate by averaging a number of samples over a long image sequence. The proposed approach has been successfully tested by many experiments, and can operate at 20 frames/s on an 800 MHz PC.

DEPTH PREDICTION OF RAIN WATER ON ROAD SURFACE BASED ON ARTIFICIAL NEURAL NETWORK

A model based on the non-linear artificial neural network （ANN） is established to predict the thickness of the water film on road surfaces. The weight and the threshold can be determined by training test data, and the water film thickness on the road surface can be accurately predicted by the empirical verification based on sample data. Results show that the proposed ANN model is feasible to predict the water film thickness of the road surface.

Study of pile shaft resistance in clayey soils

Based on principal component analysis, the rules of clayey soil's behaviors affected by varied indices were studied. It was discovered that the common method of the single liquidity index IL used to determine the consistency of silt-clay or silt-loam was not rational. It was more rational that the liquidity index IL combined with the void ratio e characterized the behavior of silt-clay. Similarly the index of e depicted the nature of sandy loam more rationally than IL. The method of predicting the pile shafted resistance by the two indices of e and IL, which was more accurate, was obtained by the methodology of back propagation (BP) artificial neural networks combined with principal component analysis. It was also observed that the pile shaft resistance increased with the increase of depth within a critical affect-depth ranging from 20 to 30 m, and the harder the clayey soil consistency was, the shallower the critical depth was.

Springback and tensile strength of 2A97 aluminum alloy during age forming

The analysis of variance(ANOVA), multiple quadratic regression and radial basis function artificial neural network(RBFANN) methods were used to study the springback and tensile strength in age forming of 2A97 aluminum alloy based on orthogonal array. The ANOVA analysis indicates that the springback reaches the minimum value when age forming is performed at 210 °C for 20 h using a single-curvature die with a radius of 400 mm, and the tensile strength reaches the maximum value when age forming is performed at 180 °C for 15 h using a single-curvature die with a radius of 1000 mm. The orders of the importance for the three factors of pre-deformation radius, aging temperature and aging time on the springback and tensile strength were determined. By analyzing the predicted results of the multiple quadratic regression and RBFANN methods, the prediction accuracy of the RBFANN model is higher than that of the regression model.