It is a known fact that the implementation and roll-out of time-series manufacturing data analytics is dependent on multiple factors. One of the key elements is combination of skillsets required. Nearly all modern data science methods, including machine learning have a strong mathematical/ statistical base, the right application of underlying methods, considering process understanding is important. The Domain background, Data Science / Time-series Analytics fundamentals, Statistics, ML algorithms and its application, Optimization techniques, Tool-centric expertise (Python, Data Cleansing, Deployment), etc. are essential skills required to execute different levels of analytics. Just developing tool-centric expertise doesn’t meet the requirements. Furthermore, which tool(s) to use, what features it should have, deployable solution is another consideration.
We under our ‘Pilot Guided Services Framework’, have executed many manufacturing analytics projects of different levels / processes / applications / datasets, etc. Over a period of time, we have analyzed the key challenges right from data inputs, time-stamp process data requirements (type/ Quality / Consistency), Unmeasured parameters, application of right statistical & ML methods to meet the end-objective and deployment related issues of ML models. For more insights, please go through the article here - https://dataanalytics.tridiagonal.com/80-20-principle-a-key-metric-to-apply-in-manufacturing-data-analytics/
In order to address these challenges, gaps in tools and skills, we have designed a Knowledge sharing and Learning program – ‘Bridge the Gap in Manufacturing Data Analytics’.
Objective: To provide Upskilling / training services on Manufacturing Data Analytics for better understanding the implementation of data science and modeling techniques for Process (time-series) data.
Programme Details:
Training – Basic, Advanced, Power Users
Basic: Start building Analytics Culture
- Basic understanding of Time-series / Manufacturing Process Data
- Data Preparation & Pre-processing – Data Cleansing, Conditioning, descriptive statistics
- Process Understanding and how to represent the system from data analytics perspective
- Introduction to Level of Analytics – Descriptive, Predictive, Prescriptive, etc.
- Exploratory Data Analytics - Feature identification, reduction, Covariance methods, basic formula techniques
- Basic introduction to ML libraries & statistical templates and its applications
- Use-cases examples – How Time-series data analytics is used
- Introduction to Visual Analytics and Insights
- Reports and Dashboarding
User Profile - Process engineers, Technologists, Plant operations team, Maintenance & Reliability Enggs., IT teams, etc.
Duration: Typically, 1 week. Depends on the Audience Size.
Advanced: Create Champions
- Introduction to building formulas and statistical/ ML python scripts for advanced analytics (for e.g, Root Cause Analysis, Critical Parameter Identification, Soft Sensors, etc.)
- Advanced Data modeling techniques (using Python, Jupyter Notebook, etc.) on your data and results
- Model construction, application / validation, Visualization and implementation – Right Methods (Use case-specific)
- Introduction to commercial analytics tools
- User Profile / Audience:Users (process domain experts) who have basic coding background (Python) and understanding on various Statistical/ ML algorithms to create Models and apply it for analytics
Prerequisite: Python expert in ML and its application
Duration: Typically, 1 week. Depends on the Audience Size.
Power Users: Create Best Practices
- Python-based template creation and widget building
- Soft-sensor building (using Physics-based, First-principle Models)
- Advanced reports and Dashboarding
- ML Model(s) deployment methods
- Best Practices / Guide & Methods for Data Analytics
User Profile / Audience: SMEs / Process domain experts with Mathematical Modeling, Process Modeling, Python/ML expertise
Duration: Typically, 1 week. Depends on the Audience Size.
Use Case Development – Workshops
Tridiagonal will provide analytics engineering support to identify and execute the use cases on your data with your users. We will work on the identified three (3-4) Use cases. The prerequisites in terms of the data requirements (signals/tags/volume, etc.), process details, data modeling & analytics objectives will be finalized. The use case can be worked on the Off-line / On-line data, provided the customer give an access to the data /analytics environment. We will submit the analytics outputs and ROI reports to the teams
Duration:Typically,4-6 weeks. Depends on the number of Use Cases
Custom Session
Tridiagonal Analytics Engineer can provide custom training. This can be structured around activities like reviewing a specific requirement or can involve an open discussion around your current use cases or business critical advanced use cases
Duration:Depends on the end-objective
We use Python and Jupyter Notebook for training modules. For any specific Analytics tool-centric training, we can customize the training modules and make it tool-specific.
Tridiagonal Solutions – a company specializing in providing knowledge/ insights-based solutions for the Process Industry. We are global Seeq implementation partner of Seeq -Advanced Analytics Solution.
For more details on the programme and commercial details, please contact us on analytics@tridiagonal.com
