FAN Jian¹， DOU Mingying¹， ZHAO Fei1， MA Cunzhi²， ZHANG Ruxin¹，JIN Yunfeng²， LI Shuyue¹， ZHANG Yongmin¹

1. State Key Laboratory of Heavy Oil Processing， China University of Petroleum-Beijing， Beijing 102249， China；

2. Nanjing Tianfu Software Co. ， Ltd. ， Nanjing 211100， China

Abstract

Objective　The complex gas-solid flow in fluidized beds often leads to operational failures such as particle agglomeration， distribution plate clogging， gas short-circuiting， and hydrodynamic instability， jeopardizing production safety and economic benefits.Compared to the machine learning （ML） methods， manual monitoring and signal processing in traditional approaches have limitations in signal extraction and multi-type fault differentiation. This study evaluates the feasibility of ML methods for state identification and fault diagnosis in gas-solid fluidized beds， benchmarking and optimizing typical ML models using the built-in AI model of DTEmpower. The research results provide insights into the development of artificial intelligence-based stabilization techniques for industrial fluidized bed systems.

Methods　A small cylindrical bubbling bed cold mold was constructed with transparent glass walls to visualize flow dynamics.The flow characteristics of fluid catalytic cracking （FCC） particles under normal working conditions， particle agglomeration  （10%-50% by volume）， and distribution plate blockage（ 12. 5%-62. 5% by area ） were simulated. Transient pressure pulsation signals were collected， and bed eigenvalues were calculated based on pressure sensor data. For fault diagnosis， four ML models， k-nearest neighbors （KNN）， random forest （RF）， support vector regression （SVR）， and radius nearest neighbor  （RNN）， as well as the AI-agent of DTEmpower， were selected based on their characteristics and model features. Five types of models were constructed and their model performance was validated and compared.

Results and Discussion　As particle agglomeration worsened， the bed pressure drop and density decreased steadily， while the distribution plate pressure drop fluctuated， showing an overall downward trend. Distribution plate clogging increased plate pressure drop but decreased bed pressure drop and density. The trend variations could be used to determine the operational status of fluidized beds. An experienced operator could identify simple faults from trend data but not complicated faults. To achieve accurate identification of fault category and severity under conditions of particle agglomeration and distribution plate blockage， ML methods should be used. For known fault severities（ limited domain）， the AI-agent model and KNN achieved the highest accuracy（ 88. 89%）， followed by RF（ 88. 67%） and SVR（ 19. 44%）. For unknown fault severities（ unqualified domain）， RF had the highest accuracy（ 100%）， followed by AI-agent（ 95. 84%）， SVR（ 87. 5%）， and RNN（ 87. 5%）. Overall， the KNN model demonstrated superior accuracy（ 93. 75%） and differentiation rate（ 81. 25%）， while the AI-agent also excelled in fault diagnosis under comparison.

Conclusion　This study offers insights into the development of AI-based technologies in operational stability solutions for indus⁃

trial fluidized bed systems. Through a comprehensive comparison of five mainstream ML models， the optimal model for condition monitoring and fault diagnosis in fluidized beds was identified. The proposed method can distinguish the differences between particle agglomeration and distribution plate blockage while quantitatively assessing failure severity， significantly enhancing operational safety. It provides a foundation for industrial-scale state identification and fault diagnosis systems based on actual industrial data. However， it should be noted that this study was conducted at a laboratory scale with simplified operating conditions and limited parameter variations. Future work should focus on applying these methods to industrial-scale applications. Historical DCS data should be employed， and specific reaction conditions and mechanisms should be considered， which will require specialized model adjustments.

Keywords： fluidized bed； intelligent algorithm； pressure pulsation； fault diagnosis

Get Citation: FAN Jian， DOU Mingying， ZHAO Fei， et al. Effectiveness of different machine learning models for state recognition and fault diagnosis in fluidized beds［J］. China Powder Science and Technology， 2025， 31（6）： 1−12.

Received: 2025-02-13 .Revised: 2024-03-27 ,Online: 2025-05-29

Funding Project:国家自然科学基金项目，编号： 22308377； 中核集团青年英才项目，编号： KY202212。

First Author: 凡简（2000—），女，硕士研究生，研究方向为多相反应过程强化。E-mail：jian_fan0113@163. com。

Corresponding Author: 张永民（1978—），男，教授，博士生导师，青年学术拔尖人才、 教育部新世纪优秀人才，研究方向为多相反应过程强化及装备。E-mail：zhym@cup. edu. cn。

CLC No: TQ051.13； TP181             Type Code: A

Serial No:1008-5548（2025）06-0001-12