首页|基于深度学习与SVM的电力系统项目自动查重模型构建与设计

基于深度学习与SVM的电力系统项目自动查重模型构建与设计

扫码查看
针对电力系统项目中,因文档繁多重复造成的资源时间浪费问题,研究提出基于深度学习算法对支持向量机进行优化,进而构建电力系统项目自动查重模型.研究对构建的优化支持向量机算法进行有效性验证,发现该算法的准确率为98.1%,F1值为0.87,召回率为81.3%,性能优于其他对比算法.同时,研究还对构建的电力系统项目自动查重模型进行性能对比实验,发现该模型的查重准确度为0.87,F1值为0.84,精度为81.0%,高于其他对比模型.且该模型的运行时间为2.7s,较其他模型运行速度更快.综上所述,研究提出的基于深度学习与支持向量机的电力系统项目自动查重模型可为电力系统项目的高效管理提供辅助支持.
Construction and design of automatic rechecking model of power system project based on deep learning and SVM
In view of the problem of resource and time waste caused by the duplication and duplication of documents in the power system project,it is proposed to optimize the support vector machine based on the deep learning algorithm,and then build the auto-matic re-check model of the power system project.The study verified the validity of the constructed optimized SVM algorithm,and found that its accuracy was 98.1%,the F1 value was 0.87,and the recall rate was 81.3%,which was better than the other compari-son algorithms.At the same time,the study also conducted the performance comparison experiment of the automatic rechecking model of the power system project,and found that the rechecking accuracy of the model is 0.87,the F1 value is 0.84,and the accuracy is 81.0%,which is higher than other comparison models.And the running time of this model is 2.7 s,which is faster than the other models.In conclusion,the proposed automatic weight-checking model of power system projects based on deep learning and support vector machine can provide auxiliary support for the efficient management of power system projects.

power system projectautomatic checking modeldeep learningsupport vector machinedocument management

章瑶易、周霜、张云飞

展开 >

国网上海市电力公司电力营销服务中心(计量中心),上海 200030

电力系统项目 自动查重模型 深度学习 支持向量机 文档管理

国网上海科技项目

52090D230004

2024

自动化与仪器仪表
重庆工业自动化仪表研究所,重庆市自动化与仪器仪表学会

自动化与仪器仪表

CSTPCD
影响因子:0.327
ISSN:1001-9227
年,卷(期):2024.(8)