Smart machines: laying the golden egg?
Publisert 16. oktober 2019 i AI
Greater manufacturing efficiency: it’s the golden egg we’re all looking for. But it’s getting increasingly hard to find. The solution could be smarter automation, which involves lots and lots of data (‘big data’) and data collection and data-driven modelling. The smart machine then uses the models to automatically adjust its own behaviour (i.e. machine learning).
Data collection and analysis
The first step is collecting data, from individual machines or preferably an entire production line. Analysing this big data can be done cost-effectively using today’s processing power and cloud storage. Clean data is essential for more efficient processing and the best results.
Simply displaying clearly understandable information on a screen can help your operators to identify and respond to anomalies in the process. This in itself can boost efficiency by 20% to 30%. However, as the amount of data increases, it’s harder for people to interpret it or see patterns. This is where data analysis software comes in handy. This can identify irregularities in performance data and flag any potential issues.
With more data and ‘smarter’ analysis, the result and insights become more comprehensive and accurate. For example, instead of just identifying an issue, the system can locate where the problem is in the line and how you can fix it, enhancing efficiency further.
As the amount of data increases, data management also becomes important. Collected data is often taken offline for advanced processing and pattern recognition. The resulting patterns are then transferred back to the factory to be implemented in real time by the machine.
Using data to increase automation
Automation can be taken a step further. Smart systems could identify a potential issue and then automatically adjust parts of the production line whilst the problem is being fixed. This will again increase production efficiency.
Individual smart machines with data analysis capabilities can optimise their behaviour in any situation because they ‘know’ how they’re supposed to work. They monitor their own performance, ensuring that it matches the expected behaviour. If it deviates from a standard pattern, the machine reports the issue to the system and, if possible, compensates by amending its operation.
Really smart factory automation
In the move towards developing a smart factory, the complexity of the data is a key barrier. That’s why at Omron, we’ve been implementing smarter systems into our own processes, enabling us to develop best practices. And there’s plenty to learn. When we first started looking at our processes, our data scientist spent 80% of his time just cleaning up the data!
We’re now applying what we’ve learnt to our systems and products so that you can enjoy the benefits of smart automation. However, the real value can only be seen by research in factories. We’ve therefore joined forces with selected customers to conduct experiments in smart automation to identify any bottlenecks.
Trained for success – by a smart machine!
Smart automation can also play a role in the human-machine interaction. Forpheus, Omron’s table-tennis playing robot, is a good example. It symbolises our innovative-automation! philosophy for machines combining the 3 i’s: integration, interaction, intelligence. For instance, it can observe the motion of its opponent, using cameras to watch the ball’s movement. Analysing the data from the sensors enable it to calculate movements precisely and quickly, so it can anticipate how the opponent will hit the ball and its trajectory. Forpheus then moves its paddle to intercept and hit the ball back.
By assessing how its opponent plays, this smart machine can determine their skill level and modifies its own play accordingly. If it plays at a slightly better level, the opponent will have a challenging game without becoming frustrated. This shows how smart machines could be used to train people: an ideal application for the manufacturing industry.
For instance, smart robots can assess an operator’s level of expertise when interacting with them or with their associated systems. One example is heavy lifting, where the robot takes the object’s weight but the operator makes fine placement adjustments. The robot uses its appraisal of an operator’s ability to provide training, or makes the task easier by giving them more guidance.
In addition to improved efficiency, smart automation can make work more fun. Smart machines can recognise who is at the assembly line and provide personalised interactions such as tips on how to do the job.
Without traditional engineering, there would be no integrated and interactive machines today. To make them intelligent, we just need to add a touch of data science engineering. And there lies the golden egg.
