Physics-Informed hierarchical reasoning (PIHR): A structured framework for generalizable fault diagnosis in industrial thickeners

IF 5 2区 工程技术 Q1 ENGINEERING, CHEMICAL
Shuangcheng Du , Hongjiang Wang , Zechen Sheng , Mingxu Hu
{"title":"Physics-Informed hierarchical reasoning (PIHR): A structured framework for generalizable fault diagnosis in industrial thickeners","authors":"Shuangcheng Du ,&nbsp;Hongjiang Wang ,&nbsp;Zechen Sheng ,&nbsp;Mingxu Hu","doi":"10.1016/j.mineng.2025.109778","DOIUrl":null,"url":null,"abstract":"<div><div>In the minerals processing industry, ensuring the safe and stable operation of thickeners is a primary objective. However, their complex dynamic characteristics present challenges for conventional monitoring systems in providing early warnings and diagnosing faults, especially under novel operating conditions. Existing diagnostic methods generally lack the generalization capability for unseen faults. They can exhibit limitations in resolving diagnostic ambiguity, identifying concurrent faults, or distinguishing between process anomalies and sensor failures, which can lead to delayed warnings. To address this, this study proposes a Physics-Informed Hierarchical Reasoning (PIHR) framework for thickener diagnostics, centered on a ’Decomposition-Analysis-Synthesis’ workflow. The architecture first decomposes the sensor data stream into distinct features intended to reflect different physical phenomena, such as slowly evolving bed compaction trends versus rapidly changing flocculation chemistry instability. Subsequently, specialized analytical paths, including a Transformer, assess the morphology of these trends to distinguish between, for example, linear and exponential growth, while other paths quantify the system’s degree of instability. Finally, the model performs a dynamic weighted fusion of this evidence based on physics-inspired heuristics (e.g., ’a trend is of greater significance during stable conditions’) to assess the operational risk. PIHR’s performance was evaluated across multiple dimensions. Quantitatively, it achieved a Macro F1-score of 0.885 in zero-shot diagnosis on fault types unseen during training, outperforming the baseline models. It also increased the fault warning lead time by over 12 min on average, while maintaining a True Positive Rate (TPR) above 0.91 and a False Positive Rate (FPR) below 0.015. Qualitatively, case studies illustrated the model’s ability to resolve diagnostic ambiguity, handle concurrent faults, and distinguish between process and sensor failures. Moreover, a physical consistency analysis indicated that the architecture extracts multivariate dynamic signatures from observational data that correlate with different physical states. Finally, its performance was evaluated in a 60-day continuous industrial deployment, where the system delivered 14 valid early warnings with no missed detections and assisted in averting a rake-bogging incident.</div></div>","PeriodicalId":18594,"journal":{"name":"Minerals Engineering","volume":"234 ","pages":"Article 109778"},"PeriodicalIF":5.0000,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Minerals Engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0892687525006065","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}
引用次数: 0

Abstract

In the minerals processing industry, ensuring the safe and stable operation of thickeners is a primary objective. However, their complex dynamic characteristics present challenges for conventional monitoring systems in providing early warnings and diagnosing faults, especially under novel operating conditions. Existing diagnostic methods generally lack the generalization capability for unseen faults. They can exhibit limitations in resolving diagnostic ambiguity, identifying concurrent faults, or distinguishing between process anomalies and sensor failures, which can lead to delayed warnings. To address this, this study proposes a Physics-Informed Hierarchical Reasoning (PIHR) framework for thickener diagnostics, centered on a ’Decomposition-Analysis-Synthesis’ workflow. The architecture first decomposes the sensor data stream into distinct features intended to reflect different physical phenomena, such as slowly evolving bed compaction trends versus rapidly changing flocculation chemistry instability. Subsequently, specialized analytical paths, including a Transformer, assess the morphology of these trends to distinguish between, for example, linear and exponential growth, while other paths quantify the system’s degree of instability. Finally, the model performs a dynamic weighted fusion of this evidence based on physics-inspired heuristics (e.g., ’a trend is of greater significance during stable conditions’) to assess the operational risk. PIHR’s performance was evaluated across multiple dimensions. Quantitatively, it achieved a Macro F1-score of 0.885 in zero-shot diagnosis on fault types unseen during training, outperforming the baseline models. It also increased the fault warning lead time by over 12 min on average, while maintaining a True Positive Rate (TPR) above 0.91 and a False Positive Rate (FPR) below 0.015. Qualitatively, case studies illustrated the model’s ability to resolve diagnostic ambiguity, handle concurrent faults, and distinguish between process and sensor failures. Moreover, a physical consistency analysis indicated that the architecture extracts multivariate dynamic signatures from observational data that correlate with different physical states. Finally, its performance was evaluated in a 60-day continuous industrial deployment, where the system delivered 14 valid early warnings with no missed detections and assisted in averting a rake-bogging incident.
基于物理信息的分层推理(PIHR):一种用于工业增稠机故障诊断的结构化框架
在矿物加工业中,确保浓密机的安全稳定运行是首要目标。然而,它们复杂的动态特性给传统监测系统在提供早期预警和故障诊断方面带来了挑战,特别是在新的运行条件下。现有的诊断方法普遍缺乏对未见故障的泛化能力。它们可能在解决诊断歧义、识别并发故障或区分过程异常和传感器故障方面表现出局限性,这可能导致延迟警告。为了解决这个问题,本研究提出了一个以“分解-分析-合成”工作流程为中心的稠化剂诊断的物理知情分层推理(PIHR)框架。该架构首先将传感器数据流分解为不同的特征,以反映不同的物理现象,例如缓慢演变的床层压实趋势与快速变化的絮凝化学不稳定性。随后,专门的分析路径,包括Transformer,评估这些趋势的形态,以区分线性和指数增长,而其他路径量化系统的不稳定程度。最后,该模型基于物理启发的启发式(例如,“在稳定条件下趋势更重要”)对这些证据进行动态加权融合,以评估操作风险。通过多个维度对PIHR的绩效进行评估。在数量上,它在训练中未见的故障类型的零射击诊断中获得了宏观f1得分为0.885,优于基线模型。它还使故障预警提前时间平均增加了12分钟以上,同时保持真阳性率(TPR)高于0.91,假阳性率(FPR)低于0.015。定性地,案例研究说明了该模型解决诊断歧义、处理并发故障以及区分过程和传感器故障的能力。此外,物理一致性分析表明,该体系结构从与不同物理状态相关的观测数据中提取多元动态特征。最后,在60天的连续工业部署中对其性能进行了评估,该系统提供了14次有效的早期预警,没有遗漏检测,并帮助避免了斜坡沼泽事件。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Minerals Engineering
Minerals Engineering 工程技术-工程:化工
CiteScore
8.70
自引率
18.80%
发文量
519
审稿时长
81 days
期刊介绍: The purpose of the journal is to provide for the rapid publication of topical papers featuring the latest developments in the allied fields of mineral processing and extractive metallurgy. Its wide ranging coverage of research and practical (operating) topics includes physical separation methods, such as comminution, flotation concentration and dewatering, chemical methods such as bio-, hydro-, and electro-metallurgy, analytical techniques, process control, simulation and instrumentation, and mineralogical aspects of processing. Environmental issues, particularly those pertaining to sustainable development, will also be strongly covered.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信