An Improved BP Algorithm and Its Application in Classification of Surface Defects of Steel Plate

Artificial neural network is a new approach to pattern recognition and classification. The model of multilayer perceptron （MLP） and back-propagation （BP） is used to train the algorithm in the artificial neural network. An improved fast algorithm of the BP network was presented, which adopts a singular value decomposition （SVD） and a generalized inverse matrix. It not only increases the speed of network learning but also achieves a satisfying precision. The simulation and experiment results show the effect of improvement of BP algorithm on the classification of the surface defects of steel plate.

Artificial Neural Network and Fuzzy Logic Based Techniques for Numerical Modeling and Prediction of Aluminum-5%Magnesium Alloy Doped with REM Neodymium

In this study, the mechanical properties of aluminum-5%magnesium doped with rare earth metal neodymium were evaluated. Fuzzy logic (FL) and artificial neural network (ANN) were used to model the mechanical properties of aluminum-5%magnesium (0-0.9 wt%) neodymium. The single input (SI) to the fuzzy logic and artificial neural network models was the percentage weight of neodymium, while the multiple outputs (MO) were average grain size, ultimate tensile strength, yield strength elongation and hardness. The fuzzy logic-based model showed more accurate prediction than the artificial neutral network-based model in terms of the correlation coefficient values (R).

Mechanical Properties Prediction of the Mechanical Clinching Joints Based on Genetic Algorithm and BP Neural Network

For optimal design of mechanical clinching steel-aluminum joints, the back propagation （BP） neural network is used to research the mapping relationship between joining technique parameters including sheet thickness, sheet hardness, joint bottom diameter etc., and mechanical properties of shearing and peeling in order to investigate joining technology between various material plates in the steel-aluminum hybrid structure car body. Genetic algorithm （GA） is adopted to optimize the back-propagation neural network connection weights. The training and validating samples are made by the BTM Tog-L-Loc system with different technologic parameters. The training samples＇ parameters and the corresponding joints＇ mechanical properties are supplied to the artificial neural network （ANN） for training. The validating samples＇ experimental data is used for checking up the prediction outputs. The calculation results show that GA can improve the model＇s prediction precision and generalization ability of BP neural network. The comparative analysis between the experimental data and the prediction outputs shows that ANN prediction models after training can effectively predict the mechanical properties of mechanical clinching joints and prove the feasibility and reliability of the intelligent neural networks system when used in the mechanical properties prediction of mechanical clinching joints. The prediction results can be used for a reference in the design of mechanical clinching steel-aluminum joints.

Intelligent direct analysis of physical and mechanical parameters of tunnel surrounding rock based on adaptive immunity algorithm and BP neural network

Because of complexity and non-predictability of the tunnel surrounding rock, the problem with the determination of the physical and mechanical parameters of the surrounding rock has become a main obstacle to theoretical research and numerical analysis in tunnel engineering. During design, it is a frequent practice, therefore, to give recommended values by analog based on experience. It is a key point in current research to make use of the displacement back analytic method to comparatively accurately determine the parameters of the surrounding rock whereas artificial intelligence possesses an exceptionally strong capability of identifying, expressing and coping with such complex non-linear relationships. The parameters can be verified by searching the optimal network structure, using back analysis on measured data to search optimal parameters and performing direct computation of the obtained results. In the current paper, the direct analysis is performed with the biological emulation system and the software of Fast Lagrangian Analysis of Continua (FLAC3D. The high non-linearity, network reasoning and coupling ability of the neural network are employed. The output vector required of the training of the neural network is obtained with the numerical analysis software. And the overall space search is conducted by employing the Adaptive Immunity Algorithm. As a result, we are able to avoid the shortcoming that multiple parameters and optimized parameters are easy to fall into a local extremum. At the same time, the computing speed and efficiency are increased as well. Further, in the paper satisfactory conclusions are arrived at through the intelligent direct-back analysis on the monitored and measured data at the Erdaoya tunneling project. The results show that the physical and mechanical parameters obtained by the intelligent direct-back analysis proposed in the current paper have effectively improved the recommended values in the original prospecting data. This is of practical significance to the appraisal of stability and informationization design of the surrounding rock.

Mechanical Property Prediction of Commercially Pure Titanium Welds with Artificial Neural Network

Factors that affect weld mechanical properties of commercially pure titanium have been investigated using artificial neural networks. Input data were obtained from mechanical testing of single-pass, autogenous welds, and neural network models were used to predict the ultimate tensile strength, yield strength, elongation, reduction of area, Vickers hardness and Rockwell B hardness. The results show that both oxygen and nitrogen have the most significant effects on the strength while hydrogen has the least effect over the range investigated. Predictions of the mechanical properties are shown and agree well with those obtained using the 'oxygen equivalent' (OE) equations.

Relationship between fatigue life of asphalt concrete and polypropylene/polyester fibers using artificial neural network and genetic algorithm

While various kinds of fibers are used to improve the hot mix asphalt(HMA) performance, a few works have been undertaken on the hybrid fiber-reinforced HMA. Therefore, the fatigue life of modified HMA samples using polypropylene and polyester fibers was evaluated and two models namely regression and artificial neural network(ANN) were used to predict the fatigue life based on the fibers parameters. As ANN contains many parameters such as the number of hidden layers which directly influence the prediction accuracy, genetic algorithm(GA) was used to solve optimization problem for ANN. Moreover, the trial and error method was used to optimize the GA parameters such as the population size. The comparison of the results obtained from regression and optimized ANN with GA shows that the two-hidden-layer ANN with two and five neurons in the first and second hidden layers, respectively, can predict the fatigue life of fiber-reinforced HMA with high accuracy(correlation coefficient of 0.96).

Modeling mechanical properties of GTAW welds of commercial titanium alloys with artificial neural network

Artificial neural networks (ANN) were used to model the strength, ductility and hardness of multi-pass welds deposited by gas tungsten arc welding (GTAW) in plates of commercial titanium alloys. The input parameters of the ANN are the alloy composition and heat treatment conditions and its output is one of the mechanical properties of the weld metal of titanium alloys, namely ultimate tensile strength (UTS), yield strength, elongation, reduction of the area (ROA) and hardness. The titanium alloys used in the work include commercially pure titanium, alpha or near-alpha titanium, alpha-beta titanium and beta or near-beta titanium.

基于BP神经网络的寒区再生微粉工程水泥基复合材料力学性能研究

为了探究不同低温不利条件下再生微粉ECC材料力学性能的影响,本文采用控制变量法,以再生微粉种类和取代率为研究变量,探究了再生微粉ECC在冻融循环和恒低温两种低温不利条件下的抗压和抗折强度试验。分析了再生微粉种类、再生微粉取代率、冻融循环次数、恒低温温度对再生微粉ECC力学性能的影响。最后基于BP神经网络,建立了3-6-1的冻融循环和3-3-1的恒低温BP神经网络结构抗压强度预测模型。研究结果表明:在相同的冻融循环条件下,再生混凝土微粉ECC的力学性能要高于再生砖粉ECC,且均随再生微粉取代率的增加先小幅度下降后剧烈下降,在经历150冻融循环后力学性能损失20%左右。而经历恒低温保温后的再生微粉ECC力学性能呈现出相反的变化趋势,随着低温保温温度的降低再生微粉ECC的力学强度反而呈现上升趋势,从常温到-40℃恒低温状态下力学性能提高22%左右。建立的两个低温不利条件下BP神经网络预测模型,平均相对误差分别为1.43%、1.28%,并以质量损失率和相对动弹模量为评判标准,预测试验范围内不同配合比的再生微粉ECC可经受的最大冻融循环次数。

Development of Al_2O_3/TiN Ceramie Cutting Tool Materials by Artificial Neural Networks

The artificial neural networks (ANN) which have broad application were proposed to develop multiphase ceramie cutting tool materials. Based on the back propagation algorithm of the forward multilayer perceptron, the models to predict volume content of composition in particie reinforced ceramies are established. The Al2O3/TiN ceramie cutting tool material was developed by ANN, whose mechanicai properties fully satisfy the cutting requirements.

基于麻雀搜索算法优化BP人工神经网络的短期湍流预报模型研究

提出了一种基于麻雀搜索算法优化BP人工神经网络(SSA-BP)的湍流预报模式。首先,采用BP人工神经网络作为湍流预报模型的基础框架。通过对温度、湿度、风速等气象因素的采集和处理,将其作为输入层的特征。然后,利用麻雀搜索算法对BP人工神经网络的权重和偏置进行优化。为了验证该方法的有效性,采用了来自地面气象站的大气湍流数据及气象数据进行实验。实验结果表明,SSA-BP人工神经网络能够成功预测大气湍流的发展趋势,并具有较高的预测精度和稳定性,能够充分利用大气湍流数据中的非线性特征,为湍流预测研究和实际应用提供了有力支持。

Adaptive prediction system of sintering through point based on self-organize artificial neural network

A soft sensing method of burning through point (BTP) was described and a new predictive parameter—the mathematics inflexion point of waste gas temperature curve in the middle of the strand was proposed. The artificial neural network was used in predicting BTP, modification on backpropagation algorithm was made in order to improve the convergence and self organize the hidden layer neurons. The adaptive prediction system developed on these techniques shows its characters such as fast, accuracy, less dependence on production data. The prediction of BTP can be used as operation guidance or control parameter.[

Modeling of mechanical properties of as-cast Mg-Li-Al alloys based on PSO-BP algorithm

Artificial neural networks have been widely used to predict the mechanical properties of alloys in material research.This study aims to investigate the implicit relationship between the compositions and mechanical properties of as-cast Mg-Li-Al alloys.Based on the experimental collection of the tensile strength and the elongation of representative Mg-Li-Al alloys,a momentum back-propagation(BP)neural network with a single hidden layer was established.Particle swarm optimization(PSO)was applied to optimize the BP model.In the neural network,the input variables were the contents of Mg,Li and Al,and the output variables were the tensile strength and the elongation. The results show that the proposed PSO-BP model can describe the quantitative relationship between the Mg-Li-Al alloy's composition and its mechanical properties.It is possible that the mechanical properties to be predicted without experiment by inputting the alloy composition into the trained network model.The prediction of the influence of Al addition on the mechanical properties of as-cast Mg-Li-Al alloys is consistent with the related research results.

Predicting uniaxial compressive strength of serpentinites through physical,dynamic and mechanical properties using neural networks

The uniaxial compressive strength(UCS)of intact rock is one of the most important parameters required and determined for rock mechanics studies in engineering projects.The limitations and difficulty of conducting tests on rocks,specifically on thinly bedded,highly fractured,highly porous and weak rocks,as well as the fact that these tests are destructive,expensive and time-consuming,lead to development of soft computing-based techniques.Application of artificial neural networks(ANNs)for predicting UCS has become an attractive alternative for geotechnical engineering scientists.In this study,an ANN was designed with the aim of indirectly predicting UCS through the serpentinization percentage,and physical,dynamic and mechanical characteristics of serpentinites.For this purpose,data obtained in earlier experimental work from central Greece were used.The ANN-based results were compared with the experimental ones and those obtained from previous analysis.The proposed ANN-based formula was found to be very efficient in predicting UCS values and the samples could be classified with simple physical,dynamic and mechanical tests,thus the expensive,difficult,time-consuming and destructive mechanical tests could be avoided.

BP神经网络预测船用钢焊接接头力学性能研究

采用不同成分母材和焊丝进行焊接工艺试验,研究母材成分、焊材成分、热输入和焊接位置等参数对焊接接头力学性能的影响,为进一步提升模型预测精度,通过遗传算法对BP神经网络进行优化,将优化权值和阈值赋值给BP神经网络进行建模,预测结果表明,优化模型稳定性好,提高了预测的精度和泛化能力,为焊接接头力学性能预测提供了借鉴,对船用钢和焊材冶金成分设计具有借鉴意义。

Characterization and Modeling of Mechanical Properties of Additively Manufactured Coconut Fiber-Reinforced Polypropylene Composites

In the face of the increased global campaign to minimize the emission of greenhouse gases and the need for sustainability in manufacturing, there is a great deal of research focusing on environmentally benign and renewable materials as a substitute for synthetic and petroleum-based products. Natural fiber-reinforced polymeric composites have recently been proposed as a viable alternative to synthetic materials. The current work investigates the suitability of coconut fiber-reinforced polypropylene as a structural material. The coconut fiber-reinforced polypropylene composites were developed. Samples of coconut fiber/polypropylene (PP) composites were prepared using Fused Filament Fabrication (FFF). Tests were then conducted on the mechanical properties of the composites for different proportions of coconut fibers. The results obtained indicate that the composites loaded with 2 wt% exhibited the highest tensile and flexural strength, while the ones loaded with 3 wt% had the highest compression strength. The ultimate tensile and flexural strength at 2 wt% were determined to be 34.13 MPa and 70.47 MPa respectively. The compression strength at 3 wt% was found to be 37.88 MPa. Compared to pure polypropylene, the addition of coconut fibers increased the tensile, flexural, and compression strength of the composite. In the study, an artificial neural network model was proposed to predict the mechanical properties of polymeric composites based on the proportion of fibers. The model was found to predict data with high accuracy.

基于GA-BPANN的钻井机械钻速预测模型

在钻井过程中,优化钻井技术可以降低钻井成本和减少施工事故,而钻速预测是优化钻井的基础。为了提高机械钻速(ROP)预测模型的准确性,开发了一种遗传算法优化的BP人工神经网络(GA-BPANN)的ROP预测模型。首先,采用最大信息系数(MIC)方法进行特征选择降低模型冗余,并将数据进行标准化处理。其次,利用遗传算法(GA)对BPANN的初始权重和偏置进行优化,建立ROP预测新模型。最后,将新模型与BPANN、支持向量回归(SVR)模型进行对比分析。研究结果表明,GA-BPANN模型具有较高的预测精度,同时为钻井过程中提高ROP提供科学依据。

Neural network fault diagnosis method optimization with rough set and genetic algorithms

Aiming at the disadvantages of BP model in artificial neural networks applied to intelligent fault diagnosis, neural network fault diagnosis optimization method with rough sets and genetic algorithms are presented. The neural network nodes of the input layer can be calculated and simplified through rough sets theory; The neural network nodes of the middle layer are designed through genetic algorithms training; the neural network bottom-up weights and bias are obtained finally through the combination of genetic algorithms and BP algorithms. The analysis in this paper illustrates that the optimization method can improve the performance of the neural network fault diagnosis method greatly.

基于BP神经网络对上海纤维加筋土体强度仿真预测

纤维加筋土是一种新型环保土体加固方法,为预测纤维加筋土的强度,通过BP神经网络对纤维土的强度预测进行研究。通过纳米二氧化硅和玄武岩纤维单掺数据来训练BP神经网络从而预测复掺数据。结果表明:预测的剪应力最大值与实际试验剪应力最大值差异范围在−2.350%到7.874%之间,预测得到的剪应力–剪切位移曲线决定系数基本都在0.9以上,说明了神经网络预测是可靠的,是一种对纤维土强度进行预测的一种可行办法,从而减少试验,降低成本,响应我国的“双碳”目标。

基于BP神经网络的柔顺铰链多目标稳健优化设计

为了提高柔顺铰链的稳健性,引入遗传算法和反向传播(Back Propagation,BP)神经网络方法对柔顺机构进行参数优化,运用正交试验来选出训练参数和测试参数,建立BP神经网络模型,利用神经网络的非线性拟合能力和遗传算法的全局搜索寻优能力对柔度和固有频率信噪比分别进行单目标和多目标寻找选取范围内的全局最优,不仅仅局限于选取因素水平的排列组合,也为提高柔顺铰链稳健性提供了一种新的解决途径。实验结果显示,柔顺铰链综合评价函数更优,实现了稳健优化设计的目的,证明了该方法的有效性。