New smart factory automation tools are providing food production lines with faster, more reliable, and cleaner production capacity. With the advent of smart machines and commercial AI, factories could soon make their own production decisions. Mitsubishi Electric’s Chris Evans considers the productivity benefits of smart manufacturing for food production. See the full article “smart food automation” here
The first stage is one of ensuring the data network infrastructure allows the organisation to create, move and use that data efficiently. The swift processing of this data ensures fast responsive manufacturing, that in-turn justifies investment in the latest automation technologies. Creating awareness of how technologies like IIoT and AI improve the performance and efficiency of both factory equipment and operators.
The role of the Industrial Internet of Things (IIoT)
IIoT in a food production factory links customer demand to a fast and flexible production system that increases responsiveness. By defining customer demand faster, it provides food producers with a significant competitive advantage. They can respond with smaller production batches, reduced raw material, and finished good stocks, benefiting themselves and the supply chain. For example, the food industry is following suit with individual printing and marking options designed into many new products. The effective handling of large data volumes also simplifies traceability and serialisation that are essential for many food, pharmaceutical and consumer products.
Artificial Intelligence (AI) in food production
Artificial Intelligence (AI) is at the beginning of its journey and is perfect for integrating into factory automation equipment. When combined with Advanced Analytics (AA), it extends traditional machine control architectures with advanced data processing, learning and decision-making capabilities. Together, they allow individual food production machines to automatically adjust times, synchronise complex systems and offer helpful suggestions to operators.
Control systems built around AA and AI are also responsible for machines that are self- learning and self-optimising. Moreover, they are the basis for the recent growth in predictive analytic tools used for preventing unplanned downtime. Mitsubishi Electric has developed several in-house AI algorithms and services and is positioning its developments in AI technologies under its own brand to reflect its growing importance.
Connecting the full spectrum of data sources on the plant floor to Edge Computing platforms enables more efficient processing. Here we get into the realm of Big Data Analysis used for finding patterns in data. This level of integration enables analysis of a far greater range of KPIs to drive improvements in overall equipment effectiveness (OEE).
Managing IT and OT crossover at the edge
Managing the crossover between Information Technology (IT) and Operational Technology (OT) is the next major challenge. Their successful merging depends on addressing the skills gap that exists between automation experts and IT departments. Often, the automation engineers managing the OT layer do not have extensive IT skills, while programmers and IT system architects may not have a full understanding of the automation world.
Edge computing may provide the answer by bridging this gap. Edge devices can collect and analyse data from local automation systems and make real-time production process decisions. But it also creates new challenges from system compatibility to data security and for protecting against growing cybersecurity threats.
Predicting the future
AI will play a key role in manufacturing, from vision recognition to skills learning and for predictive maintenance for failure prevention. It has further scope for providing operational benefits and efficiencies. For example, from anticipating faults and warning operators to self-optimising machine performance and increasing the effectiveness of predictive maintenance for plant automation assets.
Also, see Article Manufacturing Automation is the key