El estudio tuvo como objetivo predecir el desgaste de los liners en molinos SAG, un proceso cr\u00edtico para evitar paradas no planificadas y optimizar la eficiencia en operaciones de molienda. Para ello, se evaluaron diferentes enfoques de modelamiento, desde m\u00e9todos simples hasta t\u00e9cnicas avanzadas de machine learning.<\/p>\n\n\n\n
La base del estudio consisti\u00f3 en una recopilaci\u00f3n robusta y diversa de datos operativos reales de plantas de procesamiento de minerales. Esta informaci\u00f3n permiti\u00f3 entrenar modelos tanto espec\u00edficos por molino como generalizables.<\/p>\n\n\n\n
El enfoque metodol\u00f3gico combin\u00f3 modelos individuales con un modelo gen\u00e9rico, aplicando t\u00e9cnicas estad\u00edsticas, \u00e1rboles de decisi\u00f3n y redes neuronales. Adem\u00e1s, se utiliz\u00f3 an\u00e1lisis de componentes principales (PCA) para mejorar la robustez frente a multicolinealidad.<\/p>\n\n\n\n
Los hallazgos demuestran que es posible construir modelos gen\u00e9ricos efectivos basados en datos operativos, aunque a\u00fan hay espacio para mejorar incorporando variables cr\u00edticas que no estuvieron disponibles en el dataset original.<\/p>\n\n\n\n
Este trabajo representa un avance significativo en la predicci\u00f3n de desgaste de liners usando machine learning, especialmente en contextos de m\u00faltiples plantas con condiciones operativas variadas. Sin embargo, hay claras oportunidades de mejora.<\/p>\n\n\n\n
Dise\u00f1ar una estrategia de recolecci\u00f3n de datos m\u00e1s rica y frecuente para escalar la soluci\u00f3n.<\/p>\n\n\n\n
Incorporar datos sobre material del liner, tipo de bola y condiciones del mineral.<\/p>\n\n\n\n
Explorar modelos h\u00edbridos combinando simulaci\u00f3n f\u00edsica (DEM) con datos reales.<\/p>\n\n\n\n
fuente: https:\/\/www.mdpi.com\/2075-163X\/14\/12\/1200<\/p>\n\n\n\n
Diccionario de Variables<\/p>\n\n\n\n
features_dict = { <\/p>\n<\/details>\n\n\n\n <\/p>","protected":false},"excerpt":{"rendered":" \ud83e\udde0 1. Objective: Indicator and Predictive Model\nThe study aimed to predict the wear of liners in SAG mills through the development of a predictive model and operational indicator, enabling maintenance planning and reduction of unplanned downtime.<\/p>","protected":false},"author":1,"featured_media":621,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_uag_custom_page_level_css":"","site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[2],"tags":[],"class_list":["post-171","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-market-trends-and-analysis"],"aioseo_notices":[],"uagb_featured_image_src":{"full":["https:\/\/binsightcenter.com\/wp-content\/uploads\/2025\/05\/SAG-Mill-Manufacturer.gif",634,435,false],"thumbnail":["https:\/\/binsightcenter.com\/wp-content\/uploads\/2025\/05\/SAG-Mill-Manufacturer-150x150.gif",150,150,true],"medium":["https:\/\/binsightcenter.com\/wp-content\/uploads\/2025\/05\/SAG-Mill-Manufacturer-300x206.gif",300,206,true],"medium_large":["https:\/\/binsightcenter.com\/wp-content\/uploads\/2025\/05\/SAG-Mill-Manufacturer.gif",634,435,false],"large":["https:\/\/binsightcenter.com\/wp-content\/uploads\/2025\/05\/SAG-Mill-Manufacturer.gif",634,435,false],"1536x1536":["https:\/\/binsightcenter.com\/wp-content\/uploads\/2025\/05\/SAG-Mill-Manufacturer.gif",634,435,false],"2048x2048":["https:\/\/binsightcenter.com\/wp-content\/uploads\/2025\/05\/SAG-Mill-Manufacturer.gif",634,435,false],"trp-custom-language-flag":["https:\/\/binsightcenter.com\/wp-content\/uploads\/2025\/05\/SAG-Mill-Manufacturer-18x12.gif",18,12,true]},"uagb_author_info":{"display_name":"buangelreyobi@gmail.com","author_link":"https:\/\/binsightcenter.com\/en\/author\/buangelreyobigmail-com\/"},"uagb_comment_info":0,"uagb_excerpt":"\ud83e\udde0 1. Objetivo: Indicador y Modelo Predictivo El estudio tuvo como objetivo predecir el desgaste de los liners en molinos […]","_links":{"self":[{"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/posts\/171","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/comments?post=171"}],"version-history":[{"count":5,"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/posts\/171\/revisions"}],"predecessor-version":[{"id":626,"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/posts\/171\/revisions\/626"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/media\/621"}],"wp:attachment":[{"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/media?parent=171"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/categories?post=171"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/binsightcenter.com\/en\/wp-json\/wp\/v2\/tags?post=171"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\u00abcumulative_feed\u00bb: \u00abToneladas totales alimentadas al molino\u00bb,
\u00abcumulative_power\u00bb: \u00abPotencia total acumulada (kWh)\u00bb,
\u00abcumulative_solid_percent\u00bb: \u00abPorcentaje de s\u00f3lidos acumulado (%)\u00bb,
\u00abcumulative_critical_speed\u00bb: \u00abVelocidad cr\u00edtica acumulada del molino (%)\u00bb,
\u00abmill_diameter\u00bb: \u00abDi\u00e1metro del molino (m)\u00bb,
\u00abliner_face_angle\u00bb: \u00ab\u00c1ngulo del liner (grados)\u00bb,
\u00abliner_height\u00bb: \u00abAltura inicial del lifter (mm)\u00bb,
\u00aboperating_hours\u00bb: \u00abHoras acumuladas de operaci\u00f3n\u00bb,
\u00abore_type_code\u00bb: \u00abC\u00f3digo de tipo de mineral (categor\u00eda codificada)\u00bb,
}<\/p>\n\n\n\nimport pandas as pd
import xgboost as xgb
import shap
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_absolute_percentage_error
1. Cargar dataset
df = pd.read_csv(\u00absag_mill_wear_data.csv\u00bb)
2. Selecci\u00f3n de variables predictoras y target
features = [
\u00abcumulative_feed\u00bb, \u00abcumulative_power\u00bb, \u00abcumulative_solid_percent\u00bb,
\u00abcumulative_critical_speed\u00bb, \u00abmill_diameter\u00bb, \u00abliner_face_angle\u00bb,
\u00abliner_height\u00bb, \u00aboperating_hours\u00bb, \u00abore_type_code\u00bb
]
target = \u00abliner_wear\u00bb # Variable objetivo (ej. desgaste en mm)
X = df[features]
y = df[target]
3. Separar data en entrenamiento y prueba
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
4. Entrenar modelo XGBoost
model = xgb.XGBRegressor(n_estimators=100, max_depth=5, learning_rate=0.1, random_state=42)
model.fit(X_train, y_train)
5. Evaluaci\u00f3n de desempe\u00f1o
y_pred = model.predict(X_test)
mape = mean_absolute_percentage_error(y_test, y_pred)
print(f\u00bbMAPE: {mape:.2%}\u00bb)
6. Interpretabilidad con SHAP
explainer = shap.Explainer(model)
shap_values = explainer(X_test)
7. Visualizaci\u00f3n de importancia de variables
shap.summary_plot(shap_values, X_test, feature_names=features)<\/summary>\n