﻿ 基于人工智能的电力物资抽检策略决策支持系统研究

# 基于人工智能的电力物资抽检策略决策支持系统研究Research on Decision Support System of Electric Power Material Sampling Inspection Strategy Based on Artificial Intelligence

Abstract: The difference sampling strategy is an effective way to improve the quality management of power materials. At present, there is no pertinence to suppliers through manual sampling strategy for-mulation, which takes time and effort, and the sampling measures are not detailed and intelligent enough. In this paper, an artificial intelligence based decision support system for power material sampling inspection strategy is proposed, which is composed of a knowledge graph database and a rule database. According to the construction method of knowledge graph, the knowledge graph of supplier evaluation is established. According to the random inspection items, the supplier random inspection strategy rule base is established. Through the algorithm of inference engine, the intel-ligent matching of knowledge graph base and sampling strategy rule base is realized. The intelli-gent output of sampling strategy is realized, which lays the foundation for the management of dif-ferentiated sampling strategy and the realization of supplier sampling strategy.

1. 引言

2. 基于人工智能的抽检策略决策系统构建

2.1. 供应商评价知识图谱建立

Figure 1. The process of building knowledge graph

table 1. Transformer inspection items

2.2. 物资抽检策略规则库建立

table 2. Sampling strategy rules

1) 历史质量问题较多的物资，提高抽检量；

2) 历史质量问题较多的供应商，提高抽检量；

3) 历史质量问题较严重的供应商，提高抽检量；

4) 采购量大、金额高的物资，提高抽检量；

5) 中标量大、金额高的供应商，提高抽检量；

6) 中标单价偏低的供应商，提高抽检量；

7) 新入网的供应商，提高抽检量；

8) 采用了新技术、新材料、新部件、新工艺等的物资，提高抽检量。

2.3. 抽检策略决策支持系统架构

Figure 2. Architecture of decision support system of artificial intelligence

1) 加线。在所有兄弟结点之间加一条连线。

2) 去线。树中的每个结点，只保留它与第一个孩子结点的连线，删除它与其它孩子结点之间的连线。

3) 层次调整。以树的根节点为轴心，将整棵树顺时针旋转一定角度，使之结构层次分明。树转换为二叉树过程，如图3所示。

Figure 3. The process of transforming tree into binary tree

1) 把每棵树转换为二叉树。

2) 第一棵二叉树不动，从第二棵二叉树开始，依次把后一棵二叉树的根结点作为前一棵二叉树的根结点的右孩子，用线连接起来。森林转换为二叉树过程，如图4所示。

Figure 4. The process of transforming forest into binary tree

3. 抽检策略决策支持系统应用

Figure 5. Application architecture of sampling strategy optimization

1) 供应商质量问题获取

2) 差异化抽检策略库管理

3) 抽检策略制定

4) 抽检计划信息获取

5) 抽检策略规则匹配

6) 差异化抽检方案制定

7) 抽检方案下发

4. 结束语

[1] 井伟, 肖少非, 杨店飞. 基于分类评价的出厂试验抽检策略研究[J]. 物流工程与管理, 2018(9): 149-150.

[2] 史忠植. 高级人工智能[M]. 北京: 科学出版社, 2011.

[3] 詹金武, 李涛, 李超. 基于人工智能的TBM选型适应性评价决策支持系统[J]. 煤炭学报, 2019, 44(10): 3258-3271.

[4] 温有奎, 温浩, 乔晓东. 让知识产生智慧——基于人工智能的文本挖掘与问答技术研究[J]. 情报学报, 2019, 38(7): 722-730.

Top