基于人工神经网络的氮化锆薄膜颜色预测模型

建立了氮化锆薄膜制备工艺参数与薄膜色度参数之间的人工神经网络预测模型，结果表明，预测结果与实测结果吻合，最大色差在5．45以内。利用所建立的模型研究了单个参数对薄膜颜色的影响规律，及多参数间交互作用与薄膜颜色的关系。并且利用神经网络根据加工要求反向预测工艺参数，从而实现了对加工参数的优化选择。     

Prediction of die casting process parameters by using an artificial neural network model for zinc alloys

Pressure die casting is an important production process. In pressure die casting, the first setting of process parameters is established through guess work. Experts use their previous experience and knowledge to develop a solution for a new application. Due to rapid expansion in the die casting process to produce better quality products in a short period of time, there is ever increasing demand to replace the time-consuming and expert-reliant traditional trial and error methods of establishing process parameters. A neural network system is developed to generate the process parameters for the pressure die casting process. The system aims to replace the existing high-cost, time-consuming and expertdependent trial and error approach for determining the process parameters. The scope of this work includes analysing a physical model of the pressure die casting filling stage based on governing equations of die cavity filling and the collection of feasible casting data for the training of the network. The training data were generated by using ZN-DA3 material on a hot chamber die casting machine with a plunger diameter of 60 mm. The present network was developed using the MATLAB application toolbox. In this work, the neural network was developed by comparing three different training algorithms: i.e. error backpropagation algorithm; momentum and adaptive learning algorithm; and Levenberg-Marquardt approximation algorithm. It was found that the Levenberg-Marquardt approximation algorithm was the preferred method for this application as it reduced the sum-squared error to a small value. The accuracy of the developed network was tested by comparing the data generated from the network with those of an expert from a local die casting industry. It was established that by using this network the selection of process parameters becomes much easier, so that it can be used by a novice user without prior knowledge of the die casting process or optimization techniques.     

Developing a model for hardness prediction in water-quenched and tempered AISI 1045 steel through an artificial neural network

The aim of the current study was to develop an artificial neural network (ANN) model to predict the hardness drop of the water-quenched and tempered AISI 1045 steel specimens, as a function of tempering temperature and time parameters. In the first stage, the effects of selected tempering parameters on the hardness drop value were investigated. In the second stage, a group of data, which have been obtained from experiments, was used for training of the ANN model. Likewise, another group of experimental data was utilized for the ANN model validation. Ultimately, maximum error of the ANN prediction was determined. The agreement between the predicted values of the ANN model with the experimental data was found to be reasonably good.     

用人工神经网络预测冰蓄冷系统蓄冰时间

蓄冰时间的预测对于冰蓄冷空调系统的设计和运行控制十分重要。在本文中,作者以理论计算数据作训练集、验证集、测试集,采用BP型人工神经网络预测了板单元冰蓄冷系统的蓄冰时间．取得了令人满意的结果。与采用差分数值计算相比,用神经网络可大大缩短计算时间。     

Modelling urban air quality using artificial neural network

This paper describes the development of artificial neural network-based vehicular exhaust emission models for predicting 8-h average carbon monoxide concentrations at two air quality control regions (AQCRs) in the city of Delhi, India, viz. a typical traffic intersection (AQCR1) and a typical arterial road (AQCR2). Maximum of ten meteorological and six traffic characteristic variables have been used in the models formulation. Three scenarios were considered—considering both meteorological and traffic characteristics input parameters; only meteorological inputs; and only traffic characteristics input data. The performance of all the developed models was evaluated on the basis of index of agreement (d) and other statistical parameters, viz. the mean and the deviations of the observed and predicted concentrations, mean bias error, mean square error, systematic and unsystematic root mean square error, coefficient of determination and linear best fit constant and gradient (Willmott in B Am Meteorol Soc 63:1309, 1982). The forecast performance of the developed models, with meteorological and traffic characteristics (d=0.78 for AQCR1 and d=0.69 for AQCR2) and with only meteorological inputs (d=0.77 for AQCR1 and d=0.67 for AQCR2), were comparable with the measured data.     

Quantitative measurement of texture orientation in biomedical images using an artificial neural network

Texture orientation is one of the most important attributes used in biomedical and clinical image interpretation. It provides critical clues of continuity and connectivity useful in relating adjacent image areas. We report a novel approach in which image data are convolved with directional convolution masks and the results are used as input to an artificial neural network for classification of image areas into a number of discrete texture orientation classes. © 1998 John Wiley & Sons, Inc. Int J Imaging Syst Technol, 9, 351–355, 1998     

Modular artificial neural network for prediction of petrophysicalproperties from well log data

An application of Kohonen's self-organizing map (SOM), learning-vector quantization (LVQ) algorithms, and commonly used backpropagation neural network (BPNN) to predict petrophysical properties obtained from well-log data are presented. A modular, artificial neural network (ANN) comprising a complex network made up from a number of subnetworks is introduced. In this approach, the SOM algorithm is applied first to classify the well-log data into a predefined number of classes, This gives an indication of the lithology in the well. The classes obtained from SOM are then appended back to the training input logs for the training of supervised LVQ. After training, LVQ can be used to classify any unknown input logs. A set of BPNN that corresponds to different classes is then trained. Once the network is trained, it is then used as the classification and prediction model for subsequent input data. Results obtained from example studies using the proposed method have shown to be fast and accurate as compared to a single BPNN network     

Effective parameters modeling in compression of an austenitic stainless steel using artificial neural network

In this study, the prediction of flow stress in 304 stainless steel using artificial neural networks (ANN) has been investigated. Experimental data earlier deduced—by [S. Venugopal et al., Optimization of cold and warm workability in 304 stainless steel using instability maps, Metall. Trans. A 27A (1996) 126–199]—were collected to obtain training and test data. Temperature, strain-rate and strain were used as input layer, while the output was flow stress. The back propagation learning algorithm with three different variants and logistic sigmoid transfer function were used in the network. The results of this investigation shows that the R² values for the test and training data set are about 0.9791 and 0.9871, respectively, and the smallest mean absolute error is 14.235. With these results, we believe that the ANN can be used for prediction of flow stress as an accurate method in 304 stainless steel.     

Experimental and prediction of sintered Cu–W composite by using artificial neural networks

High-energy mechanical milling was used to mix Cu and W powders. Cylindrical preforms with initial preform density of 85% were prepared using a die and punch assembly. The preforms were sintered in an electric muffle furnace at 750 °C, 800 °C, 850 °C, and subsequently furnace cooled and then the specimens are hot extruded to get 92% preform density. Scanning Electron Microscope and X-ray diffraction observations used to evaluate the characteristics. The pore size reduction during extrusion was studied using Auto CAD 2010. Neural networks are employed to study the tribological behavior of sintered Cu–W composites. The proposed neural network model has used the measured parameters namely the weight percentage of tungsten, sintering temperature, load and sliding distance to predict multiple material characteristics, hardness, specific wear rate, and coefficient of friction. The predicted values from the proposed networks coincide with the experimental values. In addition, a relative study between the regression analysis and the networks revealed that the artificial neural networks can predict the tribological characteristics of sintered Cu and W composites better than regression polynomials within a very few percent error.     

Pore size prediction of polyethersulfone ultrafiltration membranes using artificial neural networks

This paper reports the performance of two different artificial neural networks (ANN), Multi Layer Perceptron (MLP) and Radial Basis Function (RBF) compared to conventional software for prediction of the pore size of the asymmetric polyethersulfone (PES) ultrafiltration membranes. ANN has advantages such as incredible approximation, generalization and good learning ability. The MLP are well suited for multiple inputs and multiple outputs while RBF are powerful techniques for interpolation in multidimensional space. Three experimental data sets were used to train the ANN using polyethylene glycol (PEG) of different molecular weights as additives namely as PEG 200, PEG 400 and PEG 600. The values of the pore size can be determined manually from the graph and solve it using mathematical equation. However, the mathematical solution used to determine the pore size and pore size distribution involve complicated equations and tedious. Thus, in this study, MLP and RBF are applied as an alternative method to estimate the pore size of polyethersulfone (PES) ultrafiltration membranes. The raw data needed for the training are solute separation and solute diameter. Values of solute separation were obtained from the ultrafiltration experiments and solute diameters ware calculated using mathematical equation. With the development of this ANN model, the process to estimate membrane pore size could be made easier and faster compared to mathematical solutions.     

A comparison between the modeling of a reciprocating compressor using artificial neural network and physical model

This article presents the development, validation, and comparison of two methods for modeling a reciprocating compressor. Initially, the physical mode is based on eight internal sub-processes that incorporate infinitesimal displacements according to the piston movement. Next, the analysis and modeling of the compressor through the application of artificial neural networks are presented. The input variables are: suction pressure, suction temperature, discharge pressure, and compressor rotation speed. The output parameters are: refrigerant mass flow rate, discharge temperature, and energy consumption. Both models are validated with experimental data for the refrigerants R1234yf and R134a; computer simulations show that mean relative errors are below ±10% with the physical model, and below ±1% when artificial neural networks are used. Additionally, the performance of the models is evaluated through the computation of the squared absolute error. Finally, these models are used to compute an energy comparison between both refrigerants.     

An artificial neural network model for virtual Superpave asphalt mixture design

This study presents an artificial neural network (ANN) model to predict the asphalt mixture volumetrics at Superpave gyration levels. The input data-set needed by the algorithm is composed of gradation of the mix, bulk specific gravity of aggregates, low- and high-performance grade of the binder, binder content of the mix and the target number of gyrations (i.e. N_ini, N_des and N_max). The proposed ANN model uses a three-layer scaled conjugate gradient back-propagation (feed-forward) network. The ANN was trained using data obtained from numerous roads with a total of 1817 different mix designs. Results revealed that the ANN was able to predict V_a within V_a (measured) ± 1.0% range 85–93% of the time and within V_a (measured) ± 0.5% range 60–70% of the time. Currently with the developed ANN model, Superpave mix design can take approximately between 1.5 and 4.5 days, which corresponds to 3–6 days of savings.     

Prediction of MOR and MOE of structural plywood board using an artificial neural network and comparison with a multivariate regression model

The structural application of plywood boards has increased considerably in recent years. In this context, determining plywood mechanical properties such as bending strength and modulus of elasticity through predictive models using more-easily obtained properties is a very useful tool for in-factory quality control. Artificial neural networks have demonstrated their high capacity for modelling complex relations between variables, considerably improving on results obtained through regression techniques. Four neural networks were developed to obtain these mechanical properties by determining board thickness, moisture content, specific gravity, bending strength and modulus of elasticity of test pieces of small dimensions. The results were compared with those of a regression model and in all cases the results of the present study were better.     

Network-level accident-mapping: Distance based pattern matching using artificial neural network

The objective of an accident-mapping algorithm is to snap traffic accidents onto the correct road segments. Assigning accidents onto the correct segments facilitate to robustly carry out some key analyses in accident research including the identification of accident hot-spots, network-level risk mapping and segment-level accident risk modelling. Existing risk mapping algorithms have some severe limitations: (i) they are not easily ‘transferable’ as the algorithms are specific to given accident datasets; (ii) they do not perform well in all road-network environments such as in areas of dense road network; and (iii) the methods used do not perform well in addressing inaccuracies inherent in and type of road environment. The purpose of this paper is to develop a new accident mapping algorithm based on the common variables observed in most accident databases (e.g. road name and type, direction of vehicle movement before the accident and recorded accident location). The challenges here are to: (i) develop a method that takes into account uncertainties inherent to the recorded traffic accident data and the underlying digital road network data, (ii) accurately determine the type and proportion of inaccuracies, and (iii) develop a robust algorithm that can be adapted for any accident set and road network of varying complexity. In order to overcome these challenges, a distance based pattern-matching approach is used to identify the correct road segment. This is based on vectors containing feature values that are common in the accident data and the network data. Since each feature does not contribute equally towards the identification of the correct road segments, an ANN approach using the single-layer perceptron is used to assist in “learning” the relative importance of each feature in the distance calculation and hence the correct link identification. The performance of the developed algorithm was evaluated based on a reference accident dataset from the UK confirming that the accuracy is much better than other methods.     

Modeling constitutive relationship of Ti40 alloy using artificial neural network

Constitutive relationship equation reflects the highly non-linear relationship of flow stress as function of strain, strain rate and temperature. It is a necessary mathematical model that describes basic information of materials deformation and finite element simulation. In this paper, based on the experimental data obtained from Gleeble-1500 Thermal Simulator, the constitutive relationship model for Ti40 alloy has been developed using back propagation (BP) neural network. The predicted flow stress values were compared with the experimental values. It was found that the absolute relative error between predicted and experimental data is less than 8.0%, which shows that predicted flow stress by artificial neural network (ANN) model is in good agreement with experimental results. Moreover, the ANN model could describe the whole deforming process better, indicating that the present model can provide a convenient and effective way to establish the constitutive relationship for Ti40 alloy.     

Modelling beta transus temperature of titanium alloys using artificial neural network

An artificial neural network (ANN) model is developed to simulate the non-linear relationship between the beta transus (β_tr) temperature of titanium alloys and the alloy chemistry. The input parameters to the model consist of the concentration of nine elements, i.e. Al, Cr, Fe, Mo, Sn, Si, V, Zr and O, whereas the model output is the β_tr temperature. Good performance of the ANN model was achieved. The interactions between the alloying elements were estimated based on the obtained ANN model. The results showed good agreement with experimental data. The influence of the database scale on ANN model performance was also discussed. Estimation of β_tr temperature through thermodynamic calculation was carried out as a comparison.     

Fuzzy neural network based yield prediction model for semiconductor manufacturing system

Accurate die yield prediction is very useful for improving yield, decreasing cost and maintaining good relationships with customers in the semiconductor manufacturing industry. To improve prediction accuracy of die yield, a novel fuzzy neural networks based yield prediction model is proposed in which the impact factors of yield and critical electrical test parameters are considered simultaneously and are taken as independent variables. The mapping between these independent variables and yield is constructed in the fuzzy neural network (FNN). The lineal regression between FNN-based yield predicting output and actual yield demonstrates the effectiveness of the proposed approach by historical experimental data of semiconductor fabrication line in Shanghai. The comparison experiment verifies the proposed yield prediction method improves on three traditional yield prediction methods with respect to prediction accuracy.     

A predictive model for slip resistance using artificial neural networks

This paper describes the formulation, building and validation of an artificial neural network model of the dynamic coefficient of friction (DCOF) as measured by a slip resistance testing device. The model predicts the DCOF as a function of six independent variables over a wide range of conditions. A grouped cross validation method is used to show the consistent performance of the model in predicting the DCOF for new values of the independent variables.     

Prediction of compressive properties of closed-cell aluminum foam using artificial neural network

The design of artificial neural network (ANN) is motivated by analogy of highly complex, non-linear and parallel computing power of the brain. Once a neural network is significantly trained it can predict the output results in the same knowledge domain. In the present work, ANN models are developed for the simulation of compressive properties of closed-cell aluminum foam: plateau stress, Young’s modulus and energy absorption capacity. The input variables for these models are relative density, average pore diameter and cell anisotropy ratio. Database of these properties are the results of the compression tests carried out on aluminum foams at a constant strain rate of 1 × 10⁻³ s⁻¹. The prediction accuracy of all the three models is found to be satisfactory. This work has shown the excellent capability of artificial neural network approach for the simulation of the compressive properties of closed-cell aluminum foam.