收稿日期:2022-07-05∗基金项目:横向课题《大学英语翻译技巧与实践》(SYHX-2019001)作者简介:郭春玲(1979-),女,陕西渭南人,本科,讲师。基于随机森林算法的英语自动翻译设备运行态势监测方法∗郭春玲(西安思源学院,西安710038)摘要:针对传统英语翻译服务机器人故障诊断准确率低,导致机器人设备运行监测效果变差,安全性降低的问题。基于随机森林和梯度提升树算法,将两者相结合得到RF-GBDT故障特征选择算法;然后基于GRU神经网络,提出一种改进的故障诊断混合模型,通过此模型实现翻译设备故障准确诊断和运行态势监测。试验结果表明,从39维向量至29维向量的特征选择中,提出的RF-GBDT算法运算效率提高了30%及以上。算法应用发现,提出的RF-GBDT算法的故障诊断率最高可达92.5%,相较于未进行特征选择的算法,本算法可有效提升故障诊断率。对比于其他故障诊断模型,提出的GRU混合模型的诊断准确率高达94.3%,故障诊断精度明显更高,诊断效果更好,可提升英语翻译机器人的安全性。关键词:随机森林算法;英语自动翻译;特征选择;故障诊断;GRU中图分类号:TP392文献标识码:ADOI编码:10.14016/j.cnki.1001-9227.2023.01.178MonitoringofEnglishAutomaticTranslationEquipmentBasedonRandomForestGUOChunling(InternationalSchoolofXi’anSiyuanUniversity,Xi’an710038,China)Abstract:InviewofthelowfaultaccuracyoftraditionalEnglishtranslationservicerobot,theoperationmonitoringeffectandsafetyofrobotequipmentarereduced.Basedonrandomforestandgradientliftingtreealgorithm,RF-GBDTfaultfeatureselectionalgorithmiscombined,andthenanimprovedfaultdiagnosishybridmodelbasedonGRUneuralnetworkisproposedtoachieveaccuratetranslationequipmentfaultdiagnosisandoperationsituationmonitoring.TheexperimentalresultsshowthattheoperationalefficiencyoftheproposedRF-GBDTalgorithmincreasesby30%ormorefrom39to29dimensions.Thealgo-rithmapplicationshowsthatthefaultdiagnosisrateoftheproposedRF-GBDTalgorithmcanreach92.5%.Thisalgorithmcaneffectivelyimprovethefaultdiagnosisratecomparedwiththealgorithmwithoutfeatureselection.Comparedwithotherfaultdiagnosismodels,thediagnosisaccuracyoftheGRUhybridmodelproposedinthispaperisashighas94.3%,thefaultdiag-nosisaccuracyissignificantlyhigher,andthediagnosiseffectisbetter,whichcanimpr...