Improving Product Quality Stability Through Data-Driven Analytics
Let’s Work Together
Call us directly, submit a sample or email us!
Company Background
SCG Chemicals Public Company Limited (SCGC) is one of Southeast Asia’s leading integrated petrochemical producers, supplying high-performance chemical products used in packaging, automotive, and industrial applications. Maintaining consistent product quality across large-scale continuous production units is critical to ensuring customer compliance, maximizing yield, and protecting operational profitability.
At SCG TPE, product quality stability—specifically Methanol levels in PY—was a key operational performance indicator directly affecting downstream processing efficiency and product acceptance.
At SCG TPE, product quality stability—specifically Methanol levels in PY—was a key operational performance indicator directly affecting downstream processing efficiency and product acceptance.
Challenges
SCG TPE faced persistent product quality variability driven by complex interactions between multiple process variables.
Key challenges included:
Key challenges included:
- Elevated and unstable Methanol levels affecting product specification compliance
- Reactive operator adjustments due to lack of predictive insight
- Limited visibility into true cause-and-effect relationships between process parameters and quality outcomes
- Difficulty distinguishing normal process variability from early indicators of quality degradation
- Inconsistent decision-making across shifts and operators
Quality instability led to reactive adjustments, operational uncertainty, and increased risk of off-spec production, resulting in material waste and financial loss.
Without a unified analytics framework, engineers relied on manual analysis and experience-based decisions rather than systematic, data-driven optimization.
Without a unified analytics framework, engineers relied on manual analysis and experience-based decisions rather than systematic, data-driven optimization.
Solution
SCG TPE implemented a structured analytics framework by connecting plant process historians and operational data streams into Seeq, enabling centralized, contextualized analysis and self-service analytics.
1. Historian Integration
Seeq connected to multiple plant data sources and process historians, streaming real-time and historical process data including:
1. Historian Integration
Seeq connected to multiple plant data sources and process historians, streaming real-time and historical process data including:
- Reactor temperatures and pressures
- Feed composition and flow rates
- Product quality measurements
- Operating parameters affecting Methanol formation
2. Self-Service Advanced Analytics
Using Seeq Workbench, engineers independently analysed historical process data to identify dominant drivers of Methanol variability.
Key capabilities included:
3. Operational Decision Support
Analytics results were translated into intuitive visual scorecards and monitoring dashboards, providing:
- Multivariate statistical analysis to identify critical process parameters
- Classification of production periods into “good-run” and “bad-run” conditions
- Comparative analysis to identify operating patterns associated with stable production
- Identification of process conditions leading to Methanol excursions
3. Operational Decision Support
Analytics results were translated into intuitive visual scorecards and monitoring dashboards, providing:
- Real-time quality performance visibility
- Standardized interpretation across operations and engineering teams
- Clear operating guidance for maintaining stable, compliant production
Benefits
Operational Efficiency
- Reduced reactive process adjustments
- Improved process stability and operational consistency
- Faster identification of process performance issues
Product Quality & Compliance
- Improved product quality stability
- Reduced risk of off-spec production
- Enhanced compliance with product specifications
- Improved production yield by reducing quality deviations
- Reduced material waste and reprocessing requirements
- Enabled self-service analytics for process engineers
- Improved alignment between operations, engineering, and management
- Established foundation for proactive quality management and continuous improvement
- These improvements enabled SCG TPE to transition from reactive troubleshooting to predictive, data-driven process optimization.
Cost Saving
Product quality variability directly impacts production yield, material waste, and operational efficiency. By stabilizing Methanol levels and reducing off-spec production, SCG TPE significantly improved process efficiency and reduced production losses.
For a detailed cost-saving assessment—including yield improvement modelling, waste reduction analysis, and annualized financial impact—connect with us to review the structured financial impact framework for product quality optimization.
For a detailed cost-saving assessment—including yield improvement modelling, waste reduction analysis, and annualized financial impact—connect with us to review the structured financial impact framework for product quality optimization.
