Application of Data Analytics for Manufacturing Excellence

For successful implementation of Data Analytics, the right methods (Use case-specific) needs to be followed right from Data ingestion, preparation, pre-processing, Model construction, validation and Model tuning & audit.

Data Preparation:

  • Extract & Examine data structure: Characterization of Process Data, Analysis of Operating regions, Identify changes in Operating conditions, Non-Gaussianity, Linear/Non-linear relationships, Time-series correlations, etc.
  • Samples and Variable Selection: - What kind of model/task is at hand – Monitoring vs. Quality

Data Pre-processing: Improve Quality of data, Data Transformation, Data Scaling & Normalization

  • Inconsistency in data, Outliers & gross errors, Missing Data (Deletion of samples, missing value estimation, Bayesian inference), Feature Scale difference among variables – Normalization/ Standardization, Gradient-descent algorithms (linear regression, logistic regression, Neural network) or distance-based

Model Selection, Training & Performance evaluation: Once training data set is ready

  • Data Model Construction depending on data characteristics (complexity) – Single model/ multiple model structure
  • Apply ML algorithm (Linear Regression, Logistic Regression, Decision trees, SVM, ANN, etc.)
  • Performance of model – Model validation methods (cross validation, model stability analysis, model robust analysis, parameter sensitivity analysis)

Application Development (L5)

  • Support process improvement
  • Exhaustive statistical analysis of your process development & characterization studies
  • Integrated Process Modelling
  • Scale-down model qualification
  • Risk assessment facilitation, evaluation, or linkages to development data

Process Understanding / Development (L4)

  • Support process improvement
  • Exhaustive statistical analysis of your process development & characterization studies
  • Integrated Process Modelling
  • Scale-down model qualification
  • Risk assessment facilitation, evaluation, or linkages to development data

Quality (L3)

  • Root Cause Analysis / Diagnostic Analytics
  • Yield-improvement study plans
  • Manufacturing Data mining and analysis
  • Energy Optimization and Asset Management
  • Integrated Process Modelling
  • Problem solving using statistical data mining and structured methodology

Process Engineering (L2)

  • Root Cause Analysis / Diagnostic Analytics
  • Yield-improvement study plans
  • Manufacturing Data mining and analysis
  • Energy Optimization and Asset Management
  • Integrated Process Modelling
  • Problem solving using statistical data mining and structured methodology

Operations Excellence (L1)

  • Asset Monitoring and OEE / Condition-based monitoring
  • Reliability Engg. / Predictive Maintenance
  • Soft Sensors: Optimization and development
  • Operational Anomalies, Real-time uni/multi variate parameter analysis during production
  • Benchmark plant performance and determine best practices
  • Role-Based Dashboards

Following are the application of Data Analytics (depending on the data availability and objectives to be achieved):

  1. Operational effectiveness / Productivity Analytics
  2. Process Variability & Correlation, RCA
  3. Quality & Traceability
  4. Energy & Utilities
  5. Asset Maintenance

Read more +15 July 2022 By bhagyashree.tambe@tridiagonal.com in Blog

Optical Character Recognition – OCR in Manufacturing Industry

Read more +16 May 2022 By bhagyashree.tambe@tridiagonal.com in Blog

Digital Transformation – Revolutionizing the Process Industry

Read more +21 February 2022 By bhagyashree.tambe@tridiagonal.com in Blog

Digital Transformation for the Process Industry

Read more +12 January 2022 By bhagyashree.tambe@tridiagonal.com in Blog

Machine Learning Model Monitoring in Process Industry (Post Deployment)

Truck Fleet MonitoringRead more +07 December 2021 By bhagyashree.tambe@tridiagonal.com in Metals and Mining

Truck Fleet Monitoring

TOP