Applications using Artificial Intelligence in factories to improve productivity are growing. Behind this are several factors from availability of smart machines, greater processing capabilities, increased access to sensor data. The drive to Industry 4.0/ IoT is also a significant factor. According to the Boston Consulting Group (BCG) Artificial Intelligence (AI) can reduce manufacturers conversion costs by up to 20%. Moreover, lower costs improve productivity, and this can lead to increases in sales.
Uptake and acceptance of AI in factories is not universal and early product implementations are split between product enhancements and cloud-based information processing and data analysis applications. For example, speech recognition use is growing in our private lives but has not yet made the jump to manufacturing. Applications that are making it to the workplace included to collaborative robotics, machine vision systems and predictive maintenance.
Algorithms are sequences of unambiguous instructions that computers use to solve problems. AI uses multiple algorithms working together to predict or change an outcome dependent on variables in the form of inputs and data. According to a recent blog from Omron, a key factor enabling manufacturers to gain the maximum benefit from these recent advances is the use of adaptive algorithms.
In the case of an adaptive algorithm it can change itself each time it runs, and known as machine learning (ML). This is also major steppingstone towards the development of ‘the factory of the future’.
Adaptive algorithms offer enormous potential in applications like predictive maintenance and networked, efficient production. They help users find new ways to optimise their production. Many manufacturing companies are identifying AI as an opportunity to increasing their Overall Equipment Effectiveness (OEE) and combining reduced costs with higher productivity.
Big budget, small budget
Producers have a dilemma in their approach to adopting AI. Many of the AI solutions available in the market, are big budget cloud-based solutions having significant requirements in terms of infrastructure and IT. They work with huge amounts of data, for which the preparation and processing is both laborious and time-consuming.
In terms of cost-effectiveness, the question of added value often unclear even for the providers. There is no simple way to determine how an investment in AI will provide them with a return. Another contributing factor to this confusion is the fact that mechanical system designs tend to be both complex and unique.
Creating value with AI in factories
How can designers integrate AI in factories with solutions that create tangible added value for the production process?
Rather than laboriously searching a huge volume of data for patterns, Omron’s approach is to tackle it from another direction. They integrate the algorithms into the machine control system, creating the framework for real-time optimisation at the machine. In contrast to edge computing analysing manufacturing lines using limited processing power, their AI controller features adaptive intelligence. Because it’s on the machine, it learns to distinguish normal patterns from abnormal ones for that individual machine.
The Sysmac automation platform is a complete machine solution with modules for control, motion, robotics, image processing and machine safety. The integrated AI controller is used at the points where the customer experiences the greatest efficiency problems or bottlenecks. The processes gain intelligence based on previous findings, and the improvements made drive the holistic optimisation of the entire process. Furthermore, it’s important to note that an improvement of just a few percentage points can result in significant efficiency gains and cost reductions.
As with any new technology, established automation equipment manufactures will start by enhancing their existing product by adding AI. This will accelerate and the range of product and applications will expand. It will also bring new entrants to the market with new ideas, new products and new technologies.