VIP20
本课程属于：009-AI and Machine Learning for Automotive CAE 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

Active Learning for Expensive Automotive Simulations

30 Chapters
View Course Samples Online
01
Course overview
active learning for expensive automotive simulations, key challenges, and engineering context.
expensiveautomotive
02
Automotive simulation landscape
crash, NVH, CFD, thermal, and durability simulations, cost drivers, and fidelity trade-offs.
Automotivesimulation
03
Surrogate modeling foundations
Gaussian processes, polynomial chaos, and neural network surrogates for simulation emulation.
Surrogatemodeling
04
Design of experiments for expensive simulations
space-filling, Latin hypercube, and adaptive sampling strategies.
experimentsexpensive
05
Active learning fundamentals
acquisition functions, uncertainty quantification, and exploration-exploitation trade-offs.
acquisitionfunctions
06
Bayesian optimization for simulation-based design
expected improvement, knowledge gradient, and constrained optimization.
Bayesianoptimization
07
Batch and parallel active learning
multi-point acquisition, asynchronous scheduling, and resource-aware sampling.
parallelmulti-point
08
Multi-fidelity active learning
combining low- and high-fidelity automotive simulations for cost-effective learning.
Multi-fidelitycombining
09
Active learning for crashworthiness
surrogate-assisted optimization of vehicle structures under impact loading.
crashworthinesssurrogate-assisted
10
Active learning for NVH simulations
reducing interior noise and vibration via adaptive sampling of modal and acoustic models.
NVHsimulations
11
Active learning for CFD in automotive aerodynamics
drag and lift prediction with adaptive surrogate refinement.
CFDautomotive
12
Active learning for thermal management
battery cooling and cabin climate simulations with expensive CFD and thermal models.
managementsimulations
13
Active learning for durability and fatigue
probabilistic life prediction using adaptive sampling of finite element simulations.
durabilityprobabilistic
14
Active learning for multi-physics automotive systems
coupling structural, thermal, and electromagnetic simulations.
multi-physicsautomotive
15
Active learning under uncertainty
robust design, reliability analysis, and chance-constrained optimization for automotive applications.
uncertaintyreliability
16
Active learning for calibration and validation
tuning simulation parameters against physical test data.
calibrationvalidation
17
Active learning for sensitivity analysis and dimension reduction
identifying influential parameters in expensive automotive models.
sensitivityanalysis
18
Active learning for real-time control and digital twins
online surrogate updates for vehicle dynamics and powertrain systems.
real-timesurrogate
19
Active learning for autonomous driving simulation
scenario generation, safety validation, and rare-event sampling.
autonomoussimulation
20
Active learning for battery and fuel cell simulations
electrochemical model calibration and degradation prediction.
simulationselectrochemical
21
Active learning for lightweight materials
composite and alloy design with expensive micro-mechanical simulations.
lightweightmaterials
22
Active learning for manufacturing process simulation
stamping, welding, and additive manufacturing parameter optimization.
manufacturingsimulation
23
Active learning for vehicle electrification
electric motor and power electronics thermal and electromagnetic design.
electrificationelectric
24
Active learning for noise and vibration harshness in electric vehicles
high-frequency NVH challenges and surrogate strategies.
vibrationharshness
25
Active learning for aerodynamic shape optimization
adjoint methods, morphing, and adaptive sampling for drag reduction.
aerodynamicoptimization
26
Active learning for crash pulse and occupant safety
surrogate-assisted restraint system design and injury criteria optimization.
occupantsurrogate-assisted
27
Active learning for thermal runaway propagation in battery packs
rare-event simulation and mitigation design.
propagationrare-event
28
Active learning for vehicle-to-grid and charging infrastructure
grid impact simulations and stochastic optimization.
vehicle-to-gridcharging
29
Active learning for fleet-level simulation
scaling from single-vehicle to fleet energy and emissions modeling.
fleet-levelsimulation
30
Capstone project
end-to-end active learning workflow for an expensive automotive simulation case study, from problem definition to validation.
Capstoneend-to-end