Applying artificial intelligence in manufacturing
In order to achieve company-specific objectives, artificial intelligence can be implemented to improve sensing, awareness, deciding, action, adapting and learning in physical production. For example, improving factory performance and related business results in manufacturing companies can be done through implementation of intelligent technologies that can augment human cognition and provide robotic intelligence. Also increasing IoT technologies in factories enables new ways of connecting and utilizing new data from physical production. New solutions can help in cases where, for example, tasks have above average number of defects, rework and/or delays, or tasks are difficult for human workers but cannot be improved through conventional automation because tasks involve flexibility.
Critical factors to address in AI for Manufacturing are work setting, work composition and work certainty. In particular, potential for reliable high-level autonomous production enabled by AI is affected by the distribution and regularity of work settings. Work composition includes the number and variability of materials/parts. Work certainty in assembling goods depends upon how much authority is given to individual customers. Make-to-stock (MTS) production is characterized by work certainty. By contrast, engineer-to-order production (ETO) is based on eliciting requirements from individual customers. Hence, there is little or no repetition of work certainty because individual customers have diverse requirements. The more uncertainty there is, the more challenging is autonomous transfer learning, which enables accurate autonomous adaptation. This is case even for assemble-to-order (ATO) production that offers individual customers more choice than MTS, but less authority than ETO. For example, Mercedes has replaced robots with human workers in the assembly of its S-Class sedan car, because of the number of vehicle options and the frequency with which it changes the kinds of options being offered.
For manufacturing companies, VTT can carry out impartial reviewing, rating and ranking of alternative intelligent factory technologies in accordance with company-specific objectives. In addition, VTT can improve opportunities for AI in Manufacturing through its unique methodology that incorporates a structured combination of engineering methods and rigorous quantitative measurement of the alignment of AI with company-specific production objectives.