Prediction of Hot Ductility of Low-Carbon Steels Based on BP Network

The purpose of the research is to obtain an effective method to predict the hot ductility of low-carbon steels, which will be a reference to evaluate the crack sensitivity of steels. Several sub-networks modeled from BP network were constructed for different temperature use, and the measured reduction of area (A(R)) of 12 kinds of low-carbon steels under the temperature of 600 to 1000 degreesC were processed as training samples. The result of software simulation shows that the model established is relatively effective for predicting the hot ductility of steels.

Performance of Feedback BP Networks

Through adding feedbacks in multi-layer BP networks, the network performance is improvedconsiderably compared with general BP network and Hopfield network, particularly the associative memorizing ability. In this paper, we analyze the two networks: feedback BP network and Hopfiled network andcompare the property between them. The conclusion shows that feedback BP network has more powerfulassociation memorizing ability than Hopfiled network.

The Application of BP Networks to Land Suitability Evaluation

The back propagation (BP) model of artificial neural networks (ANN) has many good qualities comparing with ordinary methods in land suitability evaluation.Through analyzing ordinary methods’ limitations,some sticking points of BP model used in land evaluation,such as network structure,learning algorithm,etc.,are discussed in detail,The land evaluation of Qionghai city is used as a case study.Fuzzy comprehensive assessment method was also employed in this evaluation for validating and comparing.

Real-time multi-step prediction control for BP network with delay

Real time multi step prediction of BP network based on dynamical compensation of system characteristics is suggested by introducing the first and second derivatives of the system and network outputs into the network input layer, and real time multi step prediction control is proposed for the BP network with delay on the basis of the results of real time multi step prediction, to achieve the simulation of real time fuzzy control of the delayed time system.

MENDED GENETIC BP NETWORK AND APPLICATION TO ROLLING FORCE PREDICTION OF 4-STAND TANDEM COLD STRIP MILL

In order to make good use of the ability to approach any function of BP (backpropagation) network and overcome its local astringency, and also make good use of the overallsearch ability of GA (genetic algorithms), a proposal to regulate the network's weights using bothGA and BP algorithms is suggested. An integrated network system of MGA (mended genetic algorithms)and BP algorithms has been established. The MGA-BP network's functions consist of optimizing GAperformance parameters, the network's structural parameters, performance parameters, and regulatingthe network's weights using both GA and BP algorithms. Rolling forces of 4-stand tandem cold stripmill are predicted by the MGA-BP network, and good results are obtained.

Classification of Infrared Monitor Images of Coal Using an Feature Texture Statistics and Improved BP Network

It is very important to accurately recognize and locate pulverized and block coal seen in a coal mine's infrared image monitoring system. Infrared monitor images of pulverized and block coal were sampled in the roadway of a coal mine. Texture statistics from the grey level dependence matrix were selected as the criterion for classification. The distributions of the texture statistics were calculated and analysed. A normalizing function was added to the front end of the BP network with one hidden layer. An additional classification layer is joined behind the linear layer. The recognition of pulverized from block coal images was tested using the improved BP network. The results of the experiment show that texture variables from the grey level dependence matrix can act as recognizable features of the image. The innovative improved BP network can then recognize the pulverized and block coal images.

Optimization of Injection Molding Process of Bearing Stand Based on BP Network Method

The quality of injection plastic molded parts relates to precise geometry,smooth surface,strength,durability,and other indicators that are associated with the mold,materials,injection process,and service environment.The warpage is one of main defects of injection products,which cost much time and materials.In order to minimize warpage to ensure the precise shape of molded parts,it needs to combine design,service conditions,process parameters,material properties,and other factors in the design and manufacturing.Finite element tools and material database are used to analyze the occurrence of warpage,and analysis results contribute to the improvement and optimization of injection molding process of typical parts.To find the optimal process parameters in the solution space,experimental data are used to establish backpropagation(BP)network for predicting warpage of a bearing stand based on analysis with Moldflow.With a proper transfer function and the BP network architecture,results from the BP network method satisfiy the criteria of accuracy.The optimal solutions are searched in the BP network by the genetic algorithm with the finding that the optimization method based on the BP network is efficient.

Forecasting Loss of Ecosystem Service Value Using a BP Network: A Case Study of the Impact of the South-to-north Water Transfer Project on the Ecological Environmental in Xiangfan, Hubei Province, China

Objective To recognize and assess the impact of the South-to-north Water Transfer Project (SNWTP) on the ecological environment of Xiangfan, Hubei Province, situated in the water-out area, and develop sound scientific countermeasures. Methods A three-layer BP network was built to simulate topology and process of the eco-economy system of Xiangfan. Historical data of ecological environmental factors and socio-economic factors as inputs, and corresponding historical data of ecosystem service value (ESV) and GDP as target outputs, were presented to train and test the network. When predicted input data after 2001 were presented to trained network as generalization sets, ESVs and GDPs of 2002, 2003, 2004... till 2050 were simulated as output in succession. Results Up to 2050, the area would have suffered an accumulative total ESV loss of RMB 104.9 billion, which accounted for 37.36% of the present ESV. The coinstantaneous GDP would change asynchronously with ESV, it would go through an up-to-down process and finally lose RMB89.3 billion, which accounted for 18.71% of 2001. Conclusions The simulation indicates that ESV loss means damage to the capability of socio-economic sustainable development, and suggests that artificial neural networks (ANNs) provide a feasible and effective method and have an important potential in ESV modeling.

Fast Quantification of the Mixture of Polycyclic Aromatic Hydrocarbons Using Surface-Enhanced Raman Spectroscopy Combined with PLS-GA-BP Network

To realize the fast and accurate quantitative analysis of the mixture of polycyclic aromatic hydrocarbons(PAHs),surface-enhanced Raman spectroscopy(SERS)coupled with multivariate calibrations were employed.In this study,three kinds of calibration algorithms were used to quantitative analysis of the mixture of naphthalene(Nap),phenanthrene(Phe),and pyrene(Pyr).Firstly,partial least squares(PLS)algorithm was used to select characteristic variables,then the global search capability of genetic algorithm(GA)was used for the determining of the initial weights and thresholds of back propagation(BP)neural network so that local minima was avoided.The PLS-GA-BP model exhibited superiority to quantify PAHs mixture,which achieved R2=0.9975,0.9710,0.9643,ARE=10.07%,19.28%,16.72%and RMSE=13.10,5.40,5.10 nmol L−1 for Nap,Phe,Pyr(in the PAHs mixture)concentration prediction respectively.The forecast error,ARE and RMSE have been reduced more than 50%and 60%respectively compared with the whole spectral BP model.The study indicates that accurate quantitative spectroscopic analysis of the mixture of PAHs samples can be achieved through the combination of SERS technique and PLS-GA-BP algorithm.

Application of genetic BP network to discriminating earthquakes and explosions

We developed a GA-BP algorithm by combining the genetic algorithm (GA) with the back propagation (BP) algorithm and established a genetic BP neural network. We also applied the BP neural network based on the BP algorithm and the genetic BP neural network based on the GA-BP algorithm to discriminate earthquakes and explosions. The obtained result shows that the discriminating performance of the genetic BP network is slightly better than that of the BP network.

Design of an Inference Engine Based on BP Network and LabVIEW

In the field of engineering, LabVIEW and MATLAB are the languages most commonly used by program developers. Howev-er, they have their respective advantages and disadvantages. The combination of the two will undoubtedly facilitate program develop-ment. Design of inference engine is the key point and difficulty in the design of fault diagnosis expert system. This paper combinesLabVIEW and MATLAB to design the inference engine of fault diagnosis expert system based on the advantages of the graphical pro-gramming environment and signal analysis toolkit of LabVIEW without the defect of neural network toolkit. In addition, it introducesthe implementation methods and precautions for combination of LabVIEW and BP network so as to make LabVIWE amd BP benefitfrom each other, which is of great pragmatic value.

Analysis of Factors Related to Vasovagal Response in Apheresis Blood Donors and the Establishment of Prediction Model Based on BP Neural Network Algorithm

Objective:To analyze the factors related to vessel vasovagal reaction(VVR)in apheresis donors,establish a mathematical model for predicting the correlation factors and occurrence risk,and use the prediction model to intervene in high-risk VVR blood donors,improve the blood donation experience,and retain blood donors.Methods:A total of 316 blood donors from the Xi'an Central Blood Bank from June to September 2022 were selected to statistically analyze VVR-related factors.A BP neural network prediction model is established with relevant factors as input and DRVR risk as output.Results:First-time blood donors had a high risk of VVR,female risk was high,and sex difference was significant(P value<0.05).The blood pressure before donation and intergroup differences were also significant(P value<0.05).After training,the established BP neural network model has a minimum RMS error of o.116,a correlation coefficient R=0.75,and a test model accuracy of 66.7%.Conclusion:First-time blood donors,women,and relatively low blood pressure are all high-risk groups for VVR.The BP neural network prediction model established in this paper has certain prediction accuracy and can be used as a means to evaluate the risk degree of clinical blood donors.

iRoot BP Plus冠髓切断术治疗乳磨牙部分不可复性牙髓炎的回顾性研究

目的 回顾性观察iRoot BP Plus冠髓切断术治疗乳磨牙部分不可复性牙髓炎的临床疗效。方法 收集2019年1月—2023年8月行乳磨牙iRoot BP Plus冠髓切断术治疗且随访24~47个月的部分不可复性牙髓炎病例102例,根据术前有无不可复性牙髓炎症状将纳入病例分为无症状组(n=53)和有症状组(n=49),观察两组的临床和影像学成功率。结果 无症状组和有症状组的临床成功率分别为96.2%和97.9%,影像学成功率分别为96.2%和93.9%。结论 在高抗菌等级前提下,iRoot BP Plus冠髓切断术可以尝试用于治疗乳磨牙部分不可复性冠髓炎。

正交实验结合AHP和GA-BP神经网络优化益黄散醇提工艺

目的 优化益黄散的醇提工艺。方法 采用回流提取法,以乙醇体积分数、液料比、提取时间为考察因素设计正交实验,以橙皮苷、川陈皮素、橘皮素、没食子酸、诃黎勒酸、诃子酸、甘草苷、甘草酸、丁香酚含量和干浸膏得率为指标,采用层次分析法(AHP)进行赋权并计算综合评分。通过验证正交实验和遗传算法(GA)-反向传播神经网络(BP神经网络)所预测的结果确定益黄散最佳醇提工艺参数。结果 正交实验优选的最佳醇提工艺参数为乙醇体积分数60%、液料比14∶1(mL/g)、提取时间90 min、提取2次,验证所得综合评分为79.19分;GA-BP神经网络优选的最佳醇提工艺参数为乙醇体积分数65%、液料比14∶1(mL/g)、提取时间60 min、提取2次,验证所得综合评分为85.30分,高于正交实验所得结果。结论 采用正交实验结合GA-BP神经网络的寻优方法较传统的正交实验寻优方法效果更佳,其优选出的益黄散最佳醇提工艺稳定可靠。

基于改进BP神经网络的河北省碳排放预测

“双碳”目标背景下,针对河北省高碳经济发展模式难以改变、以往预测模型难以满足现实需求等问题。论文根据统计年鉴数据,研究河北省能源消费趋势和分行业碳排放特征,并借助脱钩指数探究河北省碳排放动态变化趋势,选取IPCC二氧化碳排放的计算方法,基于6项碳排放量影响因素建立遗传算法(GA)优化BP神经网络的河北省碳排放模型,对河北省2021—2030年碳排放量进行仿真预测。结果显示:河北省能源效率低于全国水平,河北省工业碳排放量最高;河北省的经济增长与碳排放之间主要呈弱脱钩态势;GA-BP模型预测结果比BP模型更加稳定,误差较小,更适合用于碳排放量的预测。预测结果显示,河北省未来碳排放量呈缓慢增长趋势,以期为政府决策提供理论依据,助力河北省“双碳”目标的实现。

基于BP-DEMATEL的山西省冬小麦水足迹影响因素识别

针对山西省冬小麦水足迹历史演变及关键影响因素识别问题,分析了1993—2021年山西省冬小麦水足迹历史演变规律,利用BP神经网络-决策实验室(BP-DEMATEL)模型对冬小麦水足迹演变的关键影响因素进行识别,将其分为驱动型因素及特征型因素,并揭示了影响因素之间的作用机制。结果表明:1993—2021年山西省冬小麦水足迹及单位水足迹均呈下降趋势;2021年山西省冬小麦总水足迹为27亿m^(3)(蓝水占比57%),单位水足迹为1 122 m^(3)/t,与前期高点相比分别下降38%(较1994年)和21%(较1993年);气温、相对湿度和灌溉面积为冬小麦水足迹演变的关键驱动型因素,化肥施用量和农业机械总动力为关键特征型因素。

基于BP神经网络的重力仪高机动状态快速调平修正技术

针对平台式重力仪大机动状态后测量能力恢复慢的问题,提出一种基于BP神经网络的重力仪稳定平台快速调平修正技术。首先,针对动态重力测量在测量平台大机动状态后调平能力不足的问题,研究了基于BP神经网络的平台姿态高效、准确解算方法;其次,利用惯性元件和卫星导航系统(GNSS)的信息优化BP神经网络,形成不同条件的平台姿态提取优化模型;最后,利用模拟仿真实验和实际机载动态重力测量数据验证所提方法的有效性和准确性。实验结果表明在大机动的动态条件下采用所提方法可以扶正重力仪稳定平台,将机动后重力仪稳定平台稳定时间缩短83.3%以上,提升动态重力测量效率。

基于AE-BP模型的杨木胶合板应力损伤识别

【目的】利用声发射(AE)技术对应力损伤全过程中的杨木胶合板进行无损检测,并利用BP神经网络对AE检测结果进行识别,以提高胶合板损伤检测精度。【方法】以市场占有量较高的托盘用杨木胶合板作为研究对象,在联合AE和应力损伤试验过程中,提取6个AE特征参数,利用声发射RA-AF联合分析法区分杨木胶合板产生裂纹的类型,采用K-均值聚类分析方法确定损伤演化程度和AE特征参数之间的对应关系,利用BP神经网络建立损伤识别模型,并对识别网络进行测试训练。【结果】AE信号幅度和上升时间可有效地表征杨木胶合板应力损伤从微裂纹萌生、产生宏观裂纹至完全断裂的损伤演化过程;通过RA-AF联合分析发现:杨木胶合板在应力损伤试验第一阶段主要为剪切破坏损伤,第二、三阶段主要为拉伸破坏损伤;通过K-均值聚类分析发现损伤类型与AE峰值频率之间的存在较强对应关系,可有效的表征不同的损伤类型:在31 kHz内为基体开裂,在31~100 kHz内为脱胶分层,大于100 kHz为纤维断裂;构建AE-BP神经网络模型对应力损伤类型训练样本的拟合优度是95.94%,测试集的拟合优度是98.89%,模型总拟合优度是96.51%,网络训练效果较好。【结论】在应力承载AE监测过程中,通过构建AE-BP模型,可对杨木胶合板产生的未知损伤进行有效检测并准确识别。

基于MPSO-BP算法的四电极电化学气体传感器温度补偿研究

针对四电极电化学气体传感器的测量精度极易受环境温度影响的问题,提出一种基于粒子群优化BP神经网络算法(PSO-BP)的温度补偿方法。利用改进的PSO算法(MPSO)对BP神经网络的权值和阈值进行优化,构造四电极电化学气体传感器的温度补偿模型,并设计了气体传感器测试系统。实验结果表明,MPSO-BP算法可有效提高BP神经网络的收敛速度和泛化能力;基于MPSO-BP算法的四电极气体传感器温度补偿模型,可将温度补偿误差控制在0.1%以内。