从设备配置和材料特性预测可转移的重量损失给料机质量流的机器学习方法

IF 4.5 2区工程技术 Q2 ENGINEERING, CHEMICAL

Powder Technology Pub Date : 2025-05-20 DOI:10.1016/j.powtec.2025.121154

Carlota Mendez Torrecillas , Hikaru G. Jolliffe , Richard Elkes , Gavin Reynolds , Magdalini Aroniada , Andrew Shier , Hugh Verrier , Sara Fathollahi , John Robertson

{"title":"从设备配置和材料特性预测可转移的重量损失给料机质量流的机器学习方法","authors":"Carlota Mendez Torrecillas , Hikaru G. Jolliffe , Richard Elkes , Gavin Reynolds , Magdalini Aroniada , Andrew Shier , Hugh Verrier , Sara Fathollahi , John Robertson","doi":"10.1016/j.powtec.2025.121154","DOIUrl":null,"url":null,"abstract":"<div><div>The present work presents a model structure to predict Loss-in-Weight feeder mass flow performance equation parameters from material and equipment properties <em>via</em> three Machine Learning (ML) models using an ensemble-of-trees approach; the dataset represents 50 materials and material grades and two feeders (with multiple screws per feeder). One ML model is used for feed factor (mass/screw revolution) magnitude prediction, another for the range of feed factor decay behaviour, and a final ML model for refinement of the range to a scalar value. Feed factor magnitude is accurately predicted (test R<sup>2</sup> of 0.94, reducing to 0.84 when inputs <em>e.g.</em> material properties are missing) and decay behaviour range is predicted with good accuracy (weighted F1 score of 86.4 %, and 78.6 % with missing inputs), while decay scalar refinement is challenging due to inherent variability. The present approach can be used for equipment pre-selection to determine which feeder-screw combination will likely deliver the mass flow required.</div></div>","PeriodicalId":407,"journal":{"name":"Powder Technology","volume":"463 ","pages":"Article 121154"},"PeriodicalIF":4.5000,"publicationDate":"2025-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A Machine Learning approach to transferable Loss-in-Weight feeder mass flow prediction from equipment configuration and material properties\",\"authors\":\"Carlota Mendez Torrecillas , Hikaru G. Jolliffe , Richard Elkes , Gavin Reynolds , Magdalini Aroniada , Andrew Shier , Hugh Verrier , Sara Fathollahi , John Robertson\",\"doi\":\"10.1016/j.powtec.2025.121154\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>The present work presents a model structure to predict Loss-in-Weight feeder mass flow performance equation parameters from material and equipment properties <em>via</em> three Machine Learning (ML) models using an ensemble-of-trees approach; the dataset represents 50 materials and material grades and two feeders (with multiple screws per feeder). One ML model is used for feed factor (mass/screw revolution) magnitude prediction, another for the range of feed factor decay behaviour, and a final ML model for refinement of the range to a scalar value. Feed factor magnitude is accurately predicted (test R<sup>2</sup> of 0.94, reducing to 0.84 when inputs <em>e.g.</em> material properties are missing) and decay behaviour range is predicted with good accuracy (weighted F1 score of 86.4 %, and 78.6 % with missing inputs), while decay scalar refinement is challenging due to inherent variability. The present approach can be used for equipment pre-selection to determine which feeder-screw combination will likely deliver the mass flow required.</div></div>\",\"PeriodicalId\":407,\"journal\":{\"name\":\"Powder Technology\",\"volume\":\"463 \",\"pages\":\"Article 121154\"},\"PeriodicalIF\":4.5000,\"publicationDate\":\"2025-05-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Powder Technology\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0032591025005492\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, CHEMICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Powder Technology","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0032591025005492","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, CHEMICAL","Score":null,"Total":0}

引用次数: 0

摘要

本研究提出了一种模型结构，通过使用树集成方法的三种机器学习（ML）模型，从材料和设备特性中预测失重给料机质量流性能方程参数；该数据集代表50种材料和材料等级和两个给料器（每个给料器有多个螺钉）。一个ML模型用于进料因子（质量/螺旋旋转）量级预测，另一个用于进料因子衰减行为的范围，最后一个ML模型用于将范围细化到标量值。饲料因子的大小被准确地预测（测试R2为0.94，当输入如材料属性缺失时降至0.84），并且衰减行为范围的预测精度很高（加权F1分数为86.4%，缺失输入时为78.6%），而由于固有的可变性，衰减标量的细化具有挑战性。目前的方法可用于设备预选，以确定哪种进料-螺杆组合可能提供所需的质量流量。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A Machine Learning approach to transferable Loss-in-Weight feeder mass flow prediction from equipment configuration and material properties

The present work presents a model structure to predict Loss-in-Weight feeder mass flow performance equation parameters from material and equipment properties via three Machine Learning (ML) models using an ensemble-of-trees approach; the dataset represents 50 materials and material grades and two feeders (with multiple screws per feeder). One ML model is used for feed factor (mass/screw revolution) magnitude prediction, another for the range of feed factor decay behaviour, and a final ML model for refinement of the range to a scalar value. Feed factor magnitude is accurately predicted (test R² of 0.94, reducing to 0.84 when inputs e.g. material properties are missing) and decay behaviour range is predicted with good accuracy (weighted F1 score of 86.4 %, and 78.6 % with missing inputs), while decay scalar refinement is challenging due to inherent variability. The present approach can be used for equipment pre-selection to determine which feeder-screw combination will likely deliver the mass flow required.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Powder Technology 工程技术-工程：化工

CiteScore

9.90

自引率

15.40%

发文量

1047

审稿时长

46 days

期刊介绍： Powder Technology is an International Journal on the Science and Technology of Wet and Dry Particulate Systems. Powder Technology publishes papers on all aspects of the formation of particles and their characterisation and on the study of systems containing particulate solids. No limitation is imposed on the size of the particles, which may range from nanometre scale, as in pigments or aerosols, to that of mined or quarried materials. The following list of topics is not intended to be comprehensive, but rather to indicate typical subjects which fall within the scope of the journal's interests: Formation and synthesis of particles by precipitation and other methods. Modification of particles by agglomeration, coating, comminution and attrition. Characterisation of the size, shape, surface area, pore structure and strength of particles and agglomerates (including the origins and effects of inter particle forces). Packing, failure, flow and permeability of assemblies of particles. Particle-particle interactions and suspension rheology. Handling and processing operations such as slurry flow, fluidization, pneumatic conveying. Interactions between particles and their environment, including delivery of particulate products to the body. Applications of particle technology in production of pharmaceuticals, chemicals, foods, pigments, structural, and functional materials and in environmental and energy related matters. For materials-oriented contributions we are looking for articles revealing the effect of particle/powder characteristics (size, morphology and composition, in that order) on material performance or functionality and, ideally, comparison to any industrial standard.