AI for manufacturing

While AI is playing a key role in manufacturing, its implementation relies on a huge amount of data and AI expertise. Expanding applications for AI create a shortage of qualified workers therefore hinders companies in adopting AI to increase the productivity. Obtaining sufficient high-quality data is expensive, time-consuming, and sometimes infeasible, especially to small batch production.

• Data correction engine: Automatically detect misclassified training data and suggest revisions to improve the final AI performance.
• Synthetic data engine: Generate synthetic training data by using CAD files to reduce the required amount of real data in AI training.
• AI generation system: Automatically generate unique AI solution for user-specified manufacturing data by automated machine learning.
• Small data learning module: Flexibly transfer knowledge from unlabeled data or related tasks to learn representation and models that can generalise well in data limited regimes.

• Removing the major obstacles (data and expert) of AI adoption in various manufacturing applications by one system.
• Automating rare item or event detection, tackling cold-start problems, and adapting systems to changing production environments rapidly.
• Supporting local industries, including the SMEs, in transformation and upgrading with advanced technology to increase the competitiveness.

• Quality inspection
• Pick and Place
• Assembly
• Packaging