基于字符增强的工业设备故障命名实体识别

针对工业设备故障领域训练数据少、实体结构复杂和实体分布不均匀等问题,文中构建了工业设备故障命名实体识别语料库。为解决字符级命名实体识别模型难以表示工业设备故障领域的专业词汇信息问题,文中提出一种基于字符增强的工业设备故障命名实体识别模型。在嵌入层,直接在RoBERTa-WWM(Robustly Optimized BERT Pretraining Approach with Whole Word Masking)的Transformer层之间融入专业词汇信息,将单词信息分配给其包含的每个字来达到增强语义的目的,通过BiLSTM(Bidirectional Long Short-Term Memory)获得全局语义信息,利用CRF(Conditional Random Field)学习相邻标签之间的依赖关系,以获得最佳句子级标签序列。实验结果证明,所提模型对工业设备故障命名实体识别任务具有良好的效果,平均F1值达到了92.403%。

应用人工智能技术提高环保设备故障识别率的研究与应用

本论文以燃煤电厂烟气治理环保岛设备为研究对象,基于人工智能大数据技术探索研发设备故障识别技术,解决环保岛设备故障识别准确率低、故障发现不及时等问题。经实验测试和应用结果表明,本文所提出的环保设备异常诊断模型识别准确率、召回率、虚警率和漏警率能达到较高水平,能实现对燃煤电厂环保设备的异常状态监测与高效精准维护。

我国红外诊断技术的现状与展望

评述了红外诊断技术在我国电力、电子、石油化工等工业设备故障诊断、热设备和建筑物热损耗诊断、材料及结构件加工缺陷无损检验和医疗诊断等领域的应用情况和发展水平，并对这一高技术的进一步发展提出了一些看法。

Overview of the Importance of Intelligent Approaches on Machinery Faults Diagnosis and Prediction Based on Prognostic and Health Management/Condition-Based Maintenance

Condition monitoring is increasingly used to anticipate and detect failures of industrial machines.Failures of machines can cause high maintenance or replacement costs.If neglected,it may result in catastrophic accidents leading to production shrinkage.The potential failure would negatively affect the profitability of the company,including production shut down,cost of spare parts,cost of labor,damage of reputation,risk of injury to people and the environment.In recent years,condition-based maintenance( CBM) and prognostic and health management( PHM) are developed and formed a strong connection among science,engineering,computer,reliability,communication,management,etc.Computerized maintenance management systems( CMMS) store a lot of data regarding the fault diagnosis and life prediction of the machinery equipment.It's too necessary to uncover useful knowledge from the huge amount of data.It's vital to find the ways to obtain useful and concise information from these data.This information can be of great influence in the decision making of managers.This article is a review of intelligent approaches in machinery faults diagnosis and prediction based on PHM and CBM.

Industrial Equipment Troubleshooting with Imaging Technique Improved Gamma-Ray Absorption Scans

Gamma scanning is one of the most common nuclear techniques on troubleshooting industrial equipments like distillation columns and reactors. With a very simple concept, the technique is easy to implement. Searching for a competitive edge the industry has been long developing solutions to achieve better results. On the last decades, significant development has been done with the advent of new equipments, electronics, portable computers and software. Continuous scanning and wireless detection systems are examples of successful field solutions, while new software aid on reporting and data presentation. However the type and quality of the results itself has not dramatically changed since its beginning. A scan profile is simple to understand, although the process to build it can be very complex as it requires a specific blend of knowledge and abilities. Process engineering, chemical engineering, internal hydraulic project, nuclear engineering and field abilities are pre requisites for of any scan specialist. Correct data gathering, interpretation and reporting are abilities often difficult to match or requires a long time of training. The industry faces a similar difficult on the customer side, as it is always necessary to train end users to understand a report and how to use its best. This paper describes our effort on developing a new approach on the gamma scan test using image reconstruction techniques that would result on a graphic image rather than a XY plot. Direct and easier to understand, a report with graphic images would be also be accessible to a wider audience, not limited to the customers experienced with gamma scan interpretation.