.jpg)
Dr Tim Foreman, European R & D Manager, Omron Industrial Automation, highlights three key issues that are involved in implementing AI; how it can improve processes and production, and if cloud or edge computing should be implemented.
Today, machines and humans within the manufacturing arena have an interdependent relationship – both rely on each other for future developments and to be able to optimise each other’s performance rate. As the industry progresses, people are continually materialising better machines with the help of powerful software and hardware that create cost effective and innovative automation solutions. In return, machines are increasing worker efficiency and productivity, resulting in higher value for society later down the line.
The AI, edge and cloud computing relationship
Cloud and edge computing are undoubtedly two pivotal technological advancements that have and are continually impacting the progression of machines and their functionalities.
Cloud computing - the storage, management and analysis of data stored remotely on a local server or via the Internet - has fast become a familiarity within society. Although it has proved invaluable in many circumstances, questions arise as to whether it is always the best solution for businesses – and in particular, for the production line. However, recently edge computing has emerged as another promising alternative.
Edge computing enables data storage, applications and analysis to be carried out at the edge of a machine. Although there are various interpretations about what edge computing entails, data mining at the edge can be compared to a spinal reflex. Lines and devices are monitored with real-time sensors, and data at the machine level can be processed in microseconds. Real-time monitoring of a machine’s condition is a key functionality, however the data volume is limited. Despite this processing data in real-time at the edge can also enable immediate responses.
Industrial manufacturers need to carefully evaluate both options before deciding between the two, taking into account the recent arrival of new solutions involving artificial intelligence (AI) and machine learning (ML).
As a new and evolving solution, all too often companies can be eager to start implementing and using AI without being fully aware of the challenges they could face. There is no question surrounding the potential benefits AI offers, but care needs to be exercised before incorporating it into industrial applications.
So, what are the key issues involved in deploying AI and in determining how AI can improve a production line or a process, and if cloud computing or edge computing should be implemented?
Issue 1: Have you pinpointed your main challenge?
Often, the biggest challenge faced by companies is that they sometimes are unable to underline the problem they are wanting to solve. Some of them aren’t measuring any data yet, so even though they might be keen to implement AI, this will prove difficult. To solve this, companies need to start collecting and cleaning data first, before thinking about the introduction of AI. You can then start trying to obtain information from the data and then begin visualising this in a smart way. This will help your company to start realising a range of benefits.
Once this is done, you can then consider implementing AI. AI can be applied at various levels, depending on the problem you want to solve. For example, if you want to compare the performance of two factories, you can gather the data and put it into the cloud (inside or outside your enterprise), and then analyse the data to draw conclusions.
Alternatively, you might want to analyse the performance of a machine that isn’t meeting your full specifications. Therefore this is a completely different issue as it can take hours or days to complete the process. Instead, you need a solution that will run in your machine and that can identify a low-quality pattern. This is where edge computing is very useful.
The main challenge remains: what problem do you want to solve and what are the most effective tools?
Issue 2: Are you using your data efficiently?
Factory machines are a source of valuable data, but it isn’t always easy for users to access and analyse the data that these machines provide. There are often also questions into how manufacturing plants can make the most effective possible use of this data, especially when introducing AI to enhance its capabilities. The key questions that need to be addressed from the start are:
- The data: Do I have enough data? If so, which data is the most relevant and how will it be used?
- The infrastructure: What is the cost of the infrastructure?
- The outcomes: What problem needs to be solved and what increase in efficiency can be achieved by using cloud or edge computing?
Again, one of the potential drawbacks of using cloud computing within the factory setting is that it can be hard to gain a true picture of the real-time performance of equipment. There is no way of looking inside the machine to see what is happening.
However, edge computing within an industrial manufacturing environment, can allow you to look at the actual process within the machine. Real-time data processing at the edge enables an immediate response to an abnormal situation in a process. With AI at the edge, manufacturers can control complexity and security.
With edge computing, the data and the computing resources are located close to the machines. This enables users to gain real-time information about the efficiency of different aspects of their industrial automation system. This means that they can access intelligence within the machine, which in turn enables deep analysis to be carried out.
Manufacturing companies are increasingly recognising that AI can make a major contribution to their profitability by increasing their OEE, which in turn will lead to greater productivity and lower costs.
The decision – Cloud or edge computing?
Advances in technology now opens avenues for data to be processed within seconds, when prior to this programming machines in traditional machine control environments to notice and analyse patterns at a quick rate was impossible.
Despite there being clear differentiators between cloud and edge computing in the manufacturing space, there are still key uses that each possess that prevent one from cancelling the other out. If set up correctly, edge and cloud computing can co-exist complement each other in a number of ways, such as handling the computing aspect in the cloud then transferring the data to edge devices.
For factories that are beginning to use AI, both cloud and edge computing need to be evaluated carefully by manufacturers to see which is the most valuable solution for their current issue or situation.
