Intelligent Design Support System of Power Equipment Selection Based on Vector Retrieval Enhanced Large Lan‍guage Model

ZHU Weidong; HUANG Shuai; HU Qian

doi:10.3969/j.issn.1008-0198.2025.02.020

English Version Reader LoginJournal Login

您当前的位置：

首页 >

文章列表页 >

Intelligent Design Support System of Power Equipment Selection Based on Vector Retrieval Enhanced Large Lan‍guage Model

更新时间：2025-11-30

- Intelligent Design Support System of Power Equipment Selection Based on Vector Retrieval Enhanced Large Lan‍guage Model
- Vol. 45, Issue 2, Pages: 143-150(2025)
- 作者机构：
  
  杭州市电力设计院有限公司,浙江,杭州,310000
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.1008-0198.2025.02.020
  CLC： TM727
- Published Online：30 April 2025，
  
  Published：2025
- 稿件说明：
移动端阅览
朱卫东, 黄帅, 胡倩. 基于向量检索增强大语言模型的电力设备选型智能设计支持系统[J]. 湖南电力, 2025, 45(2): 143-150.

ZHU Weidong, HUANG Shuai, HU Qian. Intelligent Design Support System of Power Equipment Selection Based on Vector Retrieval Enhanced Large Lan‍guage Model[J]. 2025, 45(2): 143-150.
朱卫东, 黄帅, 胡倩. 基于向量检索增强大语言模型的电力设备选型智能设计支持系统[J]. 湖南电力, 2025, 45(2): 143-150. DOI： 10.3969/j.issn.1008-0198.2025.02.020.

ZHU Weidong, HUANG Shuai, HU Qian. Intelligent Design Support System of Power Equipment Selection Based on Vector Retrieval Enhanced Large Lan‍guage Model[J]. 2025, 45(2): 143-150. DOI： 10.3969/j.issn.1008-0198.2025.02.020.

摘要

针对当前的电力设备选型设计支持系统难以应对大规模和高复杂度的选型场景

响应速度慢、设计准确性低的问题

设计一种基于大型语言模型的向量检索增强智能设计支持系统。首先

构建专业知识向量库

将多种具体工程场景下的设计知识编码为高维向量存储在向量库中。然后

采用分组查询注意力和双块注意力机制来优化多轮检索过程

通过计算输入需求与知识库向量的相似度

实现专业知识的快速检索。最后

利用提示工程下的多轮对话和上下文跟踪

优化选型设计方案

提升系统的智能化水平。实验结果表明

该系统在多个复杂的电力设备选型场景中表现优异

可以满足电力行业对高效智能选型设计支持的需求。

Abstract

Aiming at the problem that the current power equipment selection design support system is difficult to cope with large-scale and high-complexity selection scenarios

with slow response speed and low design accuracy

a vector retrieval-enhanced intelligent design support system based on large language models is designed. Firstly

a professional knowledge vector database is constructed to encode design knowledge under diverse specific engineering scenarios into high-dimensional vectors and stored in the vector database. Then

grouped query attention and dual-block attention mechanisms are used to optimize the multi-round retrieval process

and the fast retrieval of expertise is achieved by calculating similarities between input requirements and knowledge base vectors. Finally

the multi-round dialogue and context tracking under cue engineering are used to optimize the selection design schemes and enhance system intelligence. The experimental results demonstrate the system performs well in several complex power equipment selection scenarios and can meet the power industry's demand for efficient and intelligent selection design support.

关键词

Keywords

references

李佳蓉,林今,邢学韬,等. 主动配电网中基于统一运行模型的电制氢(P2H)模块组合选型与优化规划[J]. 中国电机工程学报,2021,41(12):4021-4033.

王小龙. 电力工程技术在智能电网建设中的运用[J]. 工程技术与管理,2023,7(24):238-240.

甘德强,胡江溢,韩祯祥. 2003年国际若干停电事故思考[J]. 电力系统自动化,2004,28(3):1-4,9.

戚英威. 基于T-S模糊模型的电力设备故障分析[J]. 电子技术,2024,53(2):168-169.

杨子腾,王立志,张亮,等. 人工智能技术在电力系统故障诊断中的应用研究[J]. 科学技术创新,2021(30):12-14.

邓明. 无人机技术在智能电网中的典型应用及发展趋势[J]. 科技与创新,2022(9):93-95,99.

陈志忠,熊泽森,姚东,等. 基于知识图谱的电力杆塔主要构件识别方法研究[J]. 浙江电力,2024,43(5):100-108.

杨焰飞,曹阳. 基于深度学习的无人机拍摄图像绝缘子目标检测[J]. 激光杂志,2020,41(10):63-66.

张蕾. 基于R-CNN的绝缘子图像定位研究[D]. 北京:华北电力大学,2018.

李旭卿,李光亚,张志艺,等. 基于改进YOLOv5的电力设备轻量化检测算法[J]. 光电子技术,2024,44(1):47-53.

陈浈斐,章黄勇,马宏忠,等. 基于深度学习的电力设备故障诊断方法研究综述[J]. 电气自动化,2022,44(1):1-2,6.

吴越,吕菁. 基于深度学习的电力系统故障诊断与预测模型优化分析[J]. 电子技术,2024,53(7):226-227.

李卓,王胤喆,叶林,等. 从感知-预测-优化综述图神经网络在电力系统中的应用[J]. 中国电力,2024,57(12):2-16.

林俊炼. 基于CIM和知识图谱的配电网信息管理及应用研究[D]. 长沙:湖南大学,2023.

丁俐夫,陈颖,肖谭南,等. 基于大语言模型的新型电力系统生成式智能应用模式初探[J]. 电力系统自动化,2024,48(19):1-13.

郑伟华,李耀辉,魏振刚. 基于机器学习算法的电力系统故障诊断[J]. 电气技术与经济,2023(9):366-368,371.

陈维江,赵国亮. 以新能源为主体的新型电力系统关键技术和装备[J]. 全球能源互联网,2022,5(1):1.

唐培峰. 智能技术在电力系统自动化中的应用[J]. 电子技术,2024,53(5):357-359.

王文星. 基于深度学习的电力设备故障诊断与智能预测算法的研究[J]. 家电维修,2024(10):89-91.

CHAO M H,TRAPPEY A J C,WU C T. Emerging technologies of natural language‐enabled chatbots:a review and trend forecast using intelligent ontology extraction and patent analytics[J]. Complexity,2021,2021(1):5511866.

PAN X,LI X,LI Q,et al. Evolving to multi-modal knowledge graphs for engineering design:state-of-the-art and future challenges[J]. Journal of Engineering Design,2024:1-40.

XIAO S T,LIU Z,ZHANG P T,et al.C-pack:packed resources for general Chinese embeddings?[C]//SIGIR 2024:The 47th International ACM SIGIR Conference on Research and Development in Infarmation Retrieval. Washington DC,USA. SIGIR,2024.

BROWN T B,MANN B,RYDER N,et al.Language models are few-shot learners[C]//Proceedings of the 34th International Conference of Neural Information Processing Systems.Vancouver,BC,Canada. ACM,2020:1877-1901.

RAFFEL C,SHAZEER N,ROBERTS A,et al.Exploring the limits of transfer learning with a unified text-to-text transformer[J]. Journal of Machine Learning Research,2020,21(1):5485-5551.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

AI问答

⁰