火电厂故障诊断文本的实体抽取模型构建
Construction of entity extraction model for fault diagnosis text in thermal power plants
陈宏 1王云博 2穆思澎 3陈阳2
作者信息
- 1. 郑州大学机械与动力工程学院,郑州 450001;哈密职业技术学院机电系,新疆哈密 839099
- 2. 郑州大学机械与动力工程学院,郑州 450001
- 3. 陕西科技大学阿尔斯特学院,西安 710016
- 折叠
摘要
针对火电厂故障诊断领域文本存在实体边界模糊、文本特征不够充分、模型识别效果不明显等问题,提出一种改进BERT-BiLSTM-CRF故障诊断领域文本实体识别模型.为了提高BERT模型在中文语境下的性能,对模型参数进行改进,使用对抗训练方法提高模型精度,使模型F1值提高0.020 6.对已构建的数据集进行实体命名识别实验,实验结果表明:改进BERT-BiLSTM-CRF实体识别模型在数据集上的F1值达到0.901 6,相较于其他模型F1值有所提升,验证了该模型的有效性.
Abstract
To address such issues as blurred entity boundaries,insufficient text features,and unremarkable model recognition effects in the field of fault diagnosis for thermal power plants,we propose a text entity recognition model based on improved BERT-BiLSTM-CRF for fault diagnosis.Entity naming recognition experiments are conducted on a newly built dataset.Our results indicate the entity recognition model based on the improved BERT-BiLSTM-CRF achieves an F1 score of 0.901 6,which is superior to those of other models,validating the effectiveness of our model.To enhance the performance of the BERT model in a Chinese context,model parameters are optimized,and adversarial training methods are employed to improve model accuracy,which is up by 0.020 6 in F1 score.
关键词
实体命名识别/预训练语言模型/火电厂/故障诊断/对抗训练Key words
entity naming recognition/pre-trained language model/thermal power plants/fault diagnosis/adversarial training引用本文复制引用
出版年
2024
国家科技期刊平台
NSTL
万方数据