Smart factories and data models

SmartFutures 21 August 2019  

Moving into the smart factory revolution, it is guaranteed to bring smarter automation into the workplace, and with this comes innovative solutions. Nevertheless, how can manufacturing efficiency be improved? First things first, it all starts with a deep dive into the data. Tim Foreman, European R&D manager, Omron, reports.

So what if it was possible to develop a machine that was capable of learning to predict when a major element of manufacturing equipment was at risk of breaking down? In addition, had the ability to pre-order spare parts in advance? Yes, this may sound like wishful thinking, yet they do exist in the form of machines with integrated artificial intelligence. These lengths are possible through the collection of data used to create specific models. Machine learning is finally executed when the data-inspired evaluating models are put into practice, used to adjust the machine’s unique behaviour through machine learning.

The first step is collecting data, from individual machines or preferably from an entire production line. This can result in lots of data – what we call big data. Up to a point, analysing all this data can be handled effectively and cheaply using today’s processing power and cloud storage. Clean data is essential to enable more efficient processing and the best results. Simply by displaying this collected information on a screen, in an easy-to understand way, can help operators identify and respond to anomalies in the process.

Data analysis helps operators

Displaying process operation data in this way can already deliver 20%-30% efficiency increases. However, as the amount of data increases, humans are less able to interpret it or perceive patterns. By incorporating large data analysis software, computers offer a more accurate and tireless tool to support humans. These tools can identify irregularities in performance data and flag potential issues to the operator.

With more data and more advanced or ‘smarter’ analysis, the insights and results become more comprehensive and accurate. For example, instead of just identifying an issue, the system can locate exactly where the problem is in the line and what needs to be done to fix it. The operator’s job is made easier and line efficiency is further optimised.

As the amount of data increases, data management also becomes important. Collected data is often taken offline for advanced processing and pattern recognition. Then, the resulting patterns are transferred back to the factory to be implemented in real-time by the machine.

Using data to increase automation

We can take this automation a step further. As previously mentioned, Smart systems could identify an issue or potential issue, flag it, and then automatically adapt parts of the production line to compensate for any shortfall whilst the problem was being fixed – all within safe operating parameters. Once again, this results in even better production efficiency.

Let us consider this at the level of an individual machine. Smart machines – equipped with data analysis capabilities – can optimise their behaviour for any given situation because they ‘know’ how they are supposed to work normally. They monitor their own performance, ensuring it matches expected behaviour. If a defect or divergence from a standard pattern occurs, the machine reports the issue to the entire system and if possible, compensates for the issue by amending its operation. From a system viewpoint, any alterations must be balanced throughout the line to ensure consistent operation between machines.

Real smart factory automation

Complexity of data is one thing that makes moving to a smart factory a major challenge. We are implementing these smarter systems into our own processes, allowing us to investigate requirements and develop best practices – and there is plenty to learn. When we started looking at our own processes about two years ago, our very first data scientist spent 80% of his time just cleaning up the data.

Companies who have taken this journey can apply what they have learned to their systems and products to bring the benefits of smart automation to customers, carrying out experiments in smart automation and learning where bottlenecks occur. In the end, only by performing this research in real factories can the real value be uncovered.

Human-machine interaction

Building on data collection and analysis, smart automation can be extended into the realm of human-machine interaction. Nowadays robots have the capabilities to become budding ping-pong champions – as just one example – capable of observing the motion of an opponent facing it on the other side of the table, along with cameras that watch the ball’s movement.

Analysing data from sensors, it can calculate movement very precisely and quickly, to anticipate how the opponent will hit the ball and its trajectory. How difficult or easily they return the ball gives a clue as to one way this smart machine can be used to general advantage. By being able to assess how its opponent plays, it can determine their skill level. Robots can modify their own playing level to get the best from an opponent, if playing at a slightly better level, the opponent will have a challenging game without becoming frustrated. Hence, smart machines can also be used to train people.

On-the-job training

This training aspect can be applied to all kinds of machine applications and is ideal for the manufacturing industry. Smart robots can assess the operator’s level of expertise when interacting either with the robots themselves or with the systems being assisted by the robots – such as heavy lifting where the robot takes the weight of the object, but the operator makes fine adjustments for placement. In this case, the robot uses its appraisal of the operator’s ability to help train them or make the task easier by giving them more guidance.

With an increasing focus on data, machines equipped with artificial intelligence are becoming one of the most promising technologies of the fourth industrial revolution. In the coming years, AI is likely to further revolutionise science across all sectors. However, before such time it is vital that manufactures use their machines integrated with AI to transform production. While this provides benefits such as smart automation and improved efficiency, this can now make it far more joyous to work all smart machines, particularly robots . For example, they have the ability to provide unique interactions, personalised to specific workers, recognising who is working on the assembly line, while providing meaningful tips and advice on the job in hand. With data providing such a key role in smart factories, learning from human-interaction, this is able to boost efficiency and productivity.

There would be no interactive and integrated machines today without traditional engineering, this is vital to remember when moving into digitalised industrial future. It only takes data, lots and lots of data science, to harness machines full potential and make them ‘smart’, this is important with the need to digitalise the lifecycle of any automotive solution.