摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑发表了关于人工智能的新研究结果。根据NewsRx记者在中华人民共和国杭州的新闻报道，研究表明，"游离氯离子浓度分布对于评估氯离子环境下钢筋混凝土结构中钢筋的腐蚀风险非常重要"。我们的新闻记者引用了浙江大学科技学院的一篇研究文章：“在本研究中，获得了3150个游离氯离子浓度数据，然后采用了支持向量回归(SVR)、支持向量机回归(SVR)、支持向量机回归等三种机器学习方法采用多层感知器(MLP)和一维卷积神经网络(1D-CNN)建立模型,对粉煤灰混凝土氯离子浓度分布进行预测,结果表明:一维CNN和MLP模型对粉煤灰混凝土氯离子浓度的预测效果较好,而SVR预测能力较差。结果表明，1D-CNN模型和MLP模型均具有较高的预测能力，即预测结果与实验结果一致，总体上优于基于Fick第二定律的时变模型。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New study results on artificial intell igence have been published. According to news reporting from Hangzhou, People’s Republic of China, by NewsRx journalists, research stated, “Free chloride concen tration distribution is important for assessing the corrosion risk of steel bars in reinforced concrete structures under chloride environment.” Our news reporters obtained a quote from the research from Zhejiang University o f Technology: “In this study, a group of 3150 free chloride concentration data s ets were obtained. Afterwards, three machine learning methods, including Support Vector Regression (SVR), Multilayer Perceptron (MLP) and One- Dimensional Convol utional Neural Network (1D-CNN) were adopted to construct models to predict chlo ride concentration distribution. Results show that 1D-CNN and MLP models are bet ter at predicting the chloride concentration in fly ash concrete, whereas the pr ediction capability of SVR is relatively poor. Moreover, free chloride concentra tion prediction based on unmeasured parameters was conducted. Results show that the 1D-CNN and MLP models both have high prediction abilities, i.e., predicted r esults are consistent with experimental measurements, performing generally bette r than the time-varying model constructed based on Fick’s second law.”
NETL
NSTL