Optimizing production schedules for flexible manufacturing (MFG101)
Optimizing Production Scheduling for Flexible Manufacturing
Industry Challenges
Increasing complexities in manufacturing operations due to real-time fluctuations in demand, cycle times, and resource availability
Legacy systems and manual processes still prevalent, making it difficult to integrate and bring dynamic shop floor operations to life
Evolving business priorities, such as cost reduction, quality, maintenance, and sustainability goals, creating the need for optimized solutions
The Power of Optimization
Optimization is a proven mathematical approach in the field of prescriptive analytics that uses specialized software (solvers) to simplify decision-making
Optimization models translate key business problem characteristics into mathematical terms, including objective functions, decision variables, and business constraints
Optimization can be applied to various production scheduling scenarios, such as:
Optimal economic order quantity
Integrating equipment data and performance metrics
Optimizing energy consumption and sustainability goals
Customer Scenario: Automotive Manufacturer
The customer, a large automotive manufacturer, faced significant production scheduling challenges due to:
Competing and changing demand
Inaccurate cycle times
Labor and resource availability issues
These challenges resulted in financial impacts, such as increased overtime costs, expedited material costs, and lost opportunity costs due to downtime
AWS can help by enabling more adaptive scheduling, maximizing efficiencies, and reducing costly downtime
Key goals for the customer include:
Gaining full visibility over production planning
Reducing expected overtime
Increasing on-time delivery
Reducing expedited parts costs
Toward a Smart Factory
The vision is to have manufacturing operations that optimize themselves in real-time, with the ability to:
Instantly detect issues
Analyze millions of scenarios in seconds
Implement optimal solutions before problems arise
Continuously learn and predict maintenance needs
Adapt to demand changes and optimize energy usage
This transformation from a traditional factory to a "smart factory" can be enabled by leveraging the power of AWS services and solutions
The AWS Solution Approach
Key components of the AWS solution include:
Edge collector to gather and contextualize equipment data
Optimization engine to generate alternate scheduling solutions
Integration with production scheduling systems to implement optimal schedules
Leveraging AWS IoT services, event-driven architecture, and open-source/commercial optimization models to enable real-time, adaptive production scheduling
Next Steps
Interested parties are invited to visit the AWS kiosks to discuss their specific challenges and explore potential use cases, high-level architectures, and pilot projects
Contact information for the presenter is provided for further discussion and collaboration
These cookies are used to collect information about how you interact with this website and allow us to remember you. We use this information to improve and customize your browsing experience, as well as for analytics.
If you decline, your information won’t be tracked when you visit this website. A single cookie will be used in your browser to remember your preference.