The electronics manufacturing industry is facing unprecedented challenges due to supply chain disruptions, soaring lead times, and availability issues. With demand for electronic components growing, Electronics Manufacturing Services (EMS) and Original Equipment Manufacturers (OEM) must find innovative solutions to optimise their operations and maintain a competitive edge. This is where AI-enhanced Bill of Materials (BOM) sourcing optimisation comes into play.
The Problem and Solution: AI-Enhanced BoM Optimisation with MILP
EMS and OEM companies need to optimise the sourcing of electronic BOMs to ensure order completion, minimise costs, manage inventory, and control budgets. Mathematical optimisation is a common method for lowering costs in manufacturing industries, and the BOM is considered one of the critical documents for production planning.
Optimising the sourcing of the BOM can help companies plan purchases at minimal prices, avoid excess stock, stay on schedule, and adhere to budgets. Prevalent heuristic techniques often overlook factors like lead times, supplier availability, and component interdependencies, leading to suboptimal results and delays. Our solution combines machine learning, data mining techniques, and mixed-integer linear programming (MILP) to address these challenges.
By expanding the optimisation space with Part Matching powered by ML, the MILP model rigorously considers all real-life restrictions while ML models learn patterns to suggest approved alternatives more efficiently and effectively.
Identifying Replacement Components
Our solution features a machine learning-powered alternative search that identifies suitable replacements with the same form, fit, and functionality, focusing on in-stock or short-lead-time components. The optimisation model minimises cost and respects all sourcing restrictions.
Harnessing AI, ML, and MILP, our approach adapts to changing market conditions and supply-chain complexities, enabling EMS and OEM companies to make data-driven decisions that yield superior cost savings, lead-time reductions, and overall efficiency.
Key Advantages of AI-Enhanced BoM Sourcing Optimisation
- Dynamic Adaptation: Responds in real time to demand fluctuations, component availability, and lead-time changes for seamless order fulfilment.
- Data-Driven Insights: Leverages ML and data mining to uncover patterns and trends for significant cost and efficiency gains.
- Holistic Optimisation: Balances cost, lead time, supplier capacity, and compatibility to deliver comprehensive procurement solutions.
- Scalability: Scales across growing supply-chain networks and increasing data volumes without loss of performance.
- Continuous Improvement: ML algorithms refine predictions and recommendations over time through feedback loops.
Models and Architecture
Alternative-component models are trained on datasets of known replacements, using electrical characteristics, packaging, and manufacturer data to predict suitability. Rule-based logic extracts reference attributes (e.g., resistance, tolerance) to seed ML searches, with user feedback further improving both the rule-based and learning components.
Case Study
Presented at ESCAPE33, our case study uses a real customer BOM with hundreds of components. A standalone MILP with zero lead time yielded a cost of $183,695 and 23% backordered demand. Incorporating AI-driven alternatives increased line items by 38%, reducing backorders by 44.4% and 14%, and cutting lead time from 300 days to 240 days, while achieving a 4% cost reduction.
Use Cases
Integrated into CalcuQuote’s StockCQ platform, our part-matching solution enables EMS/OEM orgs to trade components efficiently, mitigating global shortages. It’s also embedded in QuoteCQ for rapid quoting and SearchCQ for multi-part lookups, delivering:
- Current stock levels
- Pricing data
- Quote history
- Alternate suggestions
- Manufacturer Part Number health metrics
These features streamline processes, enhance decision-making, and accelerate procurement while maintaining quality standards.
Savings: Time, Money, and Resources
Our AI-enhanced BOM sourcing model delivers tangible benefits—a 4.4% reduction in total cost and a 24% lead-time cut—while building supply-chain resilience and agility. Automated recommendations enable rapid adaptation to market shifts, avoiding delays and ensuring high-quality outputs.
Conclusion
We’ve proposed a system that unites ML, data mining, and MILP to optimise electronic BOM sourcing in EMS and OEM industries. By leveraging these technologies, companies gain cost savings, shorter lead times, and greater agility in the face of supply-chain disruptions—essential for maintaining a competitive edge and driving the future of manufacturing.
