VIP20
本课程属于：006-Data Science and Engineering Analytics 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

Engineering Root Cause Analysis with Statistical Methods

30 Chapters
View Course Samples Online
01
Foundations of engineering root cause analysis
definitions, objectives, and the role of statistical thinking in incident investigation.
Foundationsanalysis
02
Problem definition and scoping
framing failure events, defining boundaries, and formulating answerable root cause questions.
definitiondefining
03
Data collection for RCA
measurement systems, sampling strategies, data quality assessment, and metadata capture.
collectionRCA
04
Descriptive statistics for failure characterization
central tendency, dispersion, distribution shapes, and graphical summaries.
Descriptivestatistics
05
Probability distributions in reliability engineering
binomial, Poisson, exponential, Weibull, and lognormal models.
Probabilitydistributions
06
Statistical inference fundamentals
estimation, confidence intervals, and hypothesis testing for engineering decisions.
Statisticalinference
07
Comparative experiments in RCA
t-tests, ANOVA, and nonparametric alternatives for process and product comparisons.
Comparativeexperiments
08
Correlation and regression analysis
identifying relationships between process variables and failure outcomes.
Correlationregression
09
Design of experiments for root cause isolation
factorial, fractional factorial, and response surface methods.
experimentsisolation
10
Control charts and process stability
distinguishing common-cause from special-cause variation in time-ordered data.
stabilitydistinguishing
11
Measurement system analysis
gauge R&R, bias, linearity, and resolution effects on RCA conclusions.
Measurementanalysis
12
Failure mode and effects analysis with statistical prioritization
linking FMEA to quantitative risk and data.
analysisstatistical
13
Fault tree analysis and probabilistic risk assessment
Boolean logic, minimal cut sets, and uncertainty propagation.
analysisprobabilistic
14
Bayesian methods for RCA
prior elicitation, posterior updating, and decision-theoretic root cause ranking.
BayesianRCA
15
Time-to-failure and survival analysis
censoring, hazard functions, and accelerated life testing.
Time-to-failuresurvival
16
Multivariate analysis for complex failures
PCA, clustering, and discriminant analysis in high-dimensional data.
Multivariateanalysis
17
Statistical process control for root cause verification
validating corrective actions with before-after and control chart methods.
Statisticalverification
18
Change point and intervention analysis
detecting shifts in processes and quantifying the effect of corrective actions.
interventionanalysis
19
Root cause analysis of discrete event data
logistic regression and classification trees for pass/fail and defect outcomes.
analysisdiscrete
20
Spatial and temporal pattern analysis
hot spot detection, autocorrelation, and seasonality in failure data.
temporalanalysis
21
Simulation and Monte Carlo methods for RCA
modeling uncertainty, sensitivity analysis, and scenario evaluation.
SimulationRCA
22
Software and tooling for statistical RCA
R, Python, JMP, Minitab, and reproducibility practices.
Softwarestatistical
23
Case study
manufacturing defect reduction using DOE and regression to isolate a root cause.
manufacturingreduction
24
Case study
field failure investigation using Weibull analysis and Bayesian updating.
investigationanalysis
25
Case study
process excursion in chemical production using control charts and change point detection.
excursionchemical
26
Case study
software system incident RCA using log data, multivariate analysis, and causal inference.
softwareincident
27
Integrating statistical RCA with engineering workflows
8D, CAPA, and reliability-centered maintenance.
Integratingstatistical
28
Communicating RCA results
uncertainty, effect sizes, visualizations, and actionable recommendations.
CommunicatingRCA
29
Common pitfalls and cognitive biases in statistical RCA
confounding, overfitting, p-hacking, and base rate neglect.
pitfallscognitive
30
Capstone project
end-to-end statistical root cause analysis of a real or simulated engineering failure.
Capstoneend-to-end