VIP20
本课程属于：005-Artificial Intelligence and Machine Learning Engineering English Technical Courses · 共 20 门相关课程，组合学习更完整。
查看所属VIP全部课程 →
← 返回所属目录 咨询 / 购买

Supervised Machine Learning for Industrial Prediction Systems

30 Chapters
View Course Samples Online
01
Industrial prediction systems
supervised learning framing, prediction targets, and operational constraints.
Industrialprediction
02
Data acquisition and sensor telemetry
time-series logging, SCADA historians, and industrial data schemas.
acquisitiontelemetry
03
Label engineering for industrial outcomes
event definition, delay handling, and target leakage prevention.
industrialoutcomes
04
Exploratory data analysis for industrial signals
trend, seasonality, regime shifts, and anomaly inspection.
Exploratoryanalysis
05
Feature engineering for process data
rolling statistics, lag features, spectral summaries, and domain ratios.
statisticsfeatures
06
Handling missing and irregular industrial data
imputation, resampling, and alignment across asynchronous sources.
Handlingirregular
07
Data splitting strategies for temporal industrial data
time-based holdout, rolling origin, and group-aware splits.
splittingstrategies
08
Baseline models for industrial prediction
linear regression, regularized regression, and decision trees.
Baselineindustrial
09
Tree ensemble methods for tabular industrial data
random forests, gradient boosting, and XGBoost.
ensembleindustrial
10
Support vector machines and kernel methods for high-dimensional sensor features.
Support vector machines and kernel methods for high-dimensional sensor features.
machineshigh-dimensional
11
Neural network fundamentals for industrial regression and classification tasks.
Neural network fundamentals for industrial regression and classification tasks.
industrialregression
12
Sequence models for industrial time series
recurrent networks, temporal convolutions, and transformers.
Sequenceindustrial
13
Model evaluation metrics for industrial prediction
MAE, RMSE, MAPE, F1, and asymmetric cost metrics.
evaluationindustrial
14
Cross-validation and hyperparameter tuning under temporal and operational constraints.
Cross-validation and hyperparameter tuning under temporal and operational constraints.
Cross-validationhyperparameter
15
Feature selection and dimensionality reduction for high-dimensional industrial datasets.
Feature selection and dimensionality reduction for high-dimensional industrial datasets.
selectiondimensionality
16
Class imbalance and rare-event prediction in industrial fault and failure scenarios.
Class imbalance and rare-event prediction in industrial fault and failure scenarios.
imbalancerare-event
17
Uncertainty quantification for industrial predictions
conformal prediction and probabilistic regression.
Uncertaintyquantification
18
Model interpretability for industrial stakeholders
SHAP, permutation importance, and partial dependence.
interpretabilityindustrial
19
Deployment of supervised models in industrial environments
batch scoring, edge inference, and API integration.
Deploymentsupervised
20
Monitoring model performance in production
data drift, concept drift, and performance degradation detection.
Monitoringperformance
21
Retraining and model lifecycle management for industrial prediction systems.
Retraining and model lifecycle management for industrial prediction systems.
Retraininglifecycle
22
Predictive maintenance case study
remaining useful life estimation with supervised regression.
Predictivemaintenance
23
Quality prediction case study
soft sensing and yield prediction in manufacturing processes.
predictionmanufacturing
24
Energy consumption and demand forecasting case study using supervised learning.
Energy consumption and demand forecasting case study using supervised learning.
consumptionforecasting
25
Anomaly and fault detection case study
supervised classification for industrial alarm reduction.
detectionsupervised
26
Safety and risk prediction case study
supervised models for hazard and incident forecasting.
predictionsupervised
27
Scalable pipelines for industrial ML
data versioning, feature stores, and workflow orchestration.
Scalablepipelines
28
Edge and embedded deployment for industrial prediction
model compression and real-time constraints.
embeddeddeployment
29
Regulatory, ethical, and safety considerations for industrial AI systems.
Regulatory, ethical, and safety considerations for industrial AI systems.
Regulatoryconsiderations
30
Capstone project
end-to-end supervised learning solution for an industrial prediction problem.
Capstoneend-to-end