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

Industrial Data Quality Monitoring and Remediation Systems

30 Chapters
View Course Samples Online
01
Industrial data quality landscape
dimensions, sources of degradation, and business impact in process, manufacturing, and energy systems.
Industriallandscape
02
Data quality monitoring architecture
sensor-to-enterprise layers, edge gateways, historians, data lakes, and streaming pipelines.
monitoringarchitecture
03
Data profiling and baseline characterization
statistical summaries, distribution fitting, and temporal pattern discovery for industrial time-series and event data.
profilingbaseline
04
Data quality rule specification
ISO 8000, DAMA-DMBOK dimensions, and domain-specific constraints for process tags, lab data, and asset records.
specificationISO
05
Missing data detection and classification
mechanisms, patterns, and impact on control loops, KPIs, and predictive models.
detectionclassification
06
Outlier and anomaly detection for industrial sensor streams
univariate methods, robust statistics, and engineering threshold logic.
detectionindustrial
07
Multivariate anomaly detection
PCA, Mahalanobis distance, autoencoders, and their application to correlated process variables.
Multivariatedetection
08
Temporal data quality issues
timestamp misalignment, clock drift, latency, and irregular sampling in SCADA and IoT networks.
Temporaltimestamp
09
Data drift and concept drift monitoring
detection algorithms, retraining triggers, and model performance degradation in production.
monitoringdetection
10
Data quality dashboards and alerting
KPI design, threshold tuning, and integration with operations and maintenance workflows.
dashboardsalerting
11
Root cause analysis for data quality incidents
causal graphs, fault trees, and correlation analysis across data pipelines.
analysisincidents
12
Data remediation strategies
imputation, interpolation, smoothing, and model-based reconstruction for missing and corrupted values.
remediationstrategies
13
Outlier treatment and reconciliation
replacement, winsorization, filtering, and mass-balance correction in process data.
treatmentreconciliation
14
Data validation and cleansing pipelines
rule engines, data quality firewalls, and automated correction workflows.
validationcleansing
15
Master data and reference data management
asset hierarchies, tag naming conventions, and unit-of-measure consistency.
referencemanagement
16
Metadata management for industrial data
data catalogs, lineage tracking, and semantic tagging for quality context.
Metadatamanagement
17
Data quality in industrial IoT and edge computing
constrained devices, communication protocols, and lightweight monitoring.
industrialIoT
18
Streaming data quality monitoring
complex event processing, windowed aggregations, and real-time remediation actions.
Streamingmonitoring
19
Batch and historical data quality assessment
profiling large historian datasets, backfilling, and reconciliation with ERP and MES.
historicalassessment
20
Data quality for machine learning in industry
training data validation, feature quality, and monitoring of deployed models.
industrytraining
21
Case study
data quality monitoring in a continuous process plant — crude unit, reactor, or distillation column.
monitoringcontinuous
22
Case study
data quality remediation in discrete manufacturing — assembly line, CNC, or robotics telemetry.
remediationdiscrete
23
Case study
data quality in power generation and smart grids — turbine sensors, PMU data, and outage management.
generationPMU
24
Data quality governance
roles, policies, stewardship, and maturity models for industrial organizations.
governancepolicies
25
Tooling and platforms
open-source and commercial solutions for industrial data quality monitoring and remediation.
platformsopen-source
26
Integration with existing systems
OPC UA, MQTT, Sparkplug B, PI System, and data historians for quality metadata.
Integrationexisting
27
Performance and scalability considerations
high-frequency data, distributed processing, and storage optimization.
Performancescalability
28
Security and privacy in industrial data quality systems
access control, data integrity, and regulatory compliance.
Securityindustrial
29
Evaluation and continuous improvement
metrics, audits, feedback loops, and benchmarking data quality programs.
Evaluationcontinuous
30
Future trends and research directions
AI-driven remediation, digital twins, and autonomous data quality management.
researchdirections