基于神經(jīng)網(wǎng)絡(luò)的隔湖組黏性土工程地質(zhì)數(shù)據(jù)分析

打開(kāi)文本圖片集

中圖分類號(hào)：P642.2 文獻(xiàn)標(biāo)志碼：A 文章編號(hào)：2095-1329（2025）02-0080-07

Abstract： Cohesivesoil inGehuformatioisthefoundationbaringlayermostusedintheSuzhou-Wuxi-Changzouarea，anditsalso oneofthe mostcommonlyusedstratuminundergroundspacedevelopment.Weselected126geologicalboreholes toresearchthisstratum using 446 groupsofsampledata （400 groups oftrainingdataand46groups ofpredictiondata）.Weuseda neuralnetworkalgorithmto establisharelationshipmodelbetweenphysicalparametersand mechanicalparameters.Wetheninput46groupsof predictiondatainto themodeltoverifyitsreliabilityandalsousedspecificdatatoresearchtherelationshipbetweenphysicalandmechanicalparameters. Theresultsshowtat：（l）TeearsoncoelationcoefcientbetweenthepredictionrsultsandmeasureddataisoretanO8bter thantheftingesultsofmultiplelinearegressionemodelisverifedaselable.（2）Tereiscertaincoelationbetwenpyical andmechanicalparameters，andtheneuraletworkalgoritmcanexpresscoelationmodelsbetweenmultipleparameters.eneral networkalgorithallows teuderstandngofthehighvalueinteutilizationofengenggeologicalbigdata.Temethodissiple and reliable，and it can be applied in the research and analysis of data.

ey words：engineering geological; cohesive soil; Gehu formation; neural network; data analysis

對(duì)其進(jìn)行更深層次的挖掘。（剩余7726字）