Exploring Artificial Intelligence in Manufacturing

Artificial intelligence (AI) is anything but new. The discipline was co-founded by the so-called ‘father of AI’, John McCarthy, in 1956. Still, it’s recently gained significant traction in the public eye, with the launch of Open AI’s generative AI platform, Chat GPT, in November 2022.

In recent months, AI has dominated global news feeds, with businesses in all sectors exploring how to incorporate AI into their processes. As a manufacturer, you’re probably also considering the role that AI could play on your production lines.

In this blog, we will explore potential use cases for AI in the manufacturing industry, provide some tips for getting started, and discuss the role of data in any successful AI application.

What is artificial intelligence?

AI describes any application of computer software allowing machines to mimic human intelligence, be this with vision, speech, or interpretation of data, to enable problem-solving. It’s an umbrella term, that describes several methodologies, including robotics, image analysis, language processing, machine learning, and artificial neural networks.

On a basic level, artificially intelligent systems analyse data using algorithms to identify patterns. More complex systems can learn from experiences, solve problems, and make decisions without human intervention.

Today, AI applications can be identified across a wide range of industries:

Food and beverages: Campbell Soup Company uses AI to analyse consumer preference data, and agile design methodology to accelerate the development of new products.

Waste and recovery: Greyparrot an AI-generated waste analytics company, has developed computer vision systems for waste identification at materials recovery facilities.

Coding and marking: At Domino, we incorporate aspects of AI to target values for new formulations and automate testing to speed up the ink development process.

How is AI used in the manufacturing industry?

There are three key areas where AI is proving valuable in the manufacturing industry.

Error reduction: AI systems can be developed to understand and analyse all types of visual data, including data from quality control systems on production lines, to identify patterns that could indicate wider production issues and facilitate waste and error reduction.

Predictive maintenance: Data from maintenance logs and production line performance can be used to predict the performance of machinery and forecast when parts may need replacing or maintenance will be required.

Forecasting: With a thorough dataset including information on plant operations, production performance, and sales and feedback, AI systems can forecast demand, helping manufacturers to streamline inventory and pre-plan production runs.

Getting started with AI in manufacturing

Any use case for AI in manufacturing will require a large dataset with which to train an AI model. As such, manufacturers must implement systems and processes that enable consistent, reliable data collection across all necessary production activities before getting started.

Quality control data: Machine vision systems for quality control could have a significant role in AI applications. Visual quality control systems, such as Domino’s R-Series, can facilitate data collection to build the datasets required to train AI models. The same systems could also become visual input sources for analysis and decision-making, feeding directly into AI models to process the data and extract insights.

Machine metrics: Robust data production equipment will play a key role in enabling AI for predictive maintenance. Manufacturers can collect valuable insights on machine performance and diagnostics via monitoring solutions such as the Domino Cloud. Historical data can be used to train AI models, while real-time machine data can be analysed by AI algorithms to predict when maintenance is needed.

Production data: Wider production data, encompassing all parts of the production line, will be required for AI in performance optimisation, predictive maintenance, and forecasting. By integrating machines together, manufacturers can collect production data from the plant floor and consolidate it into an accessible dataset to support the deployment of AI.

Domino’s latest generation technologies have been designed with integration in mind. Simply put, everything produced on a line will have a code on it, which be counted as part of a single shift or production run to measure overall production performance. As part of a more expansive production ‘ecosystem’ within a manufacturing line, Domino’s solutions are developed to work with leading industry protocols, including Ethernet IP, to provide seamless communication between SCADA systems and all other parts of the production line.

Upstream and downstream data: Variable data coding at the batch or item level, when combined with other production monitoring systems such as those highlighted above, can be used to tie individual products back to the production line. A serialised product code will allow for the identification of products if they land in a reject pile or cause an issue at some point during distribution, providing a route to trace back and uncover precisely when and where they were made.

The value of a variable data code can extend far beyond the factory as products move through the wider supply chain and into the hands of consumers. A scannable code with a unique serial number can be used to gather customer feedback and associate it back to the product’s unique production history – this not only helps with identifying where issues arise but can also help brands to collect data on consumer preferences, trends, etc., to help develop existing or new products.

Collecting this information during production and beyond the factory doors is another part of a complex toolkit to help businesses get to a point where their data is robust enough to consider investigating AI applications.

Data is the first step in any AI journey, but it is arguably the most important part of the process without which any future attempts will be sure to fail.

Preparing for change

Preparing for an AI project in manufacturing will also involve sufficient resource allocation to implement new systems, develop datasets, train AI models, and monitor and analyse progress.

While conversations surrounding AI inevitably bring up concerns around the replacement of human workers for the short term, at least, the opposite is true.

Forbes suggests AI will enable workers to focus on more meaningful and high-value activities, while both MIT and Statista suggest that human-robot collaborations (which can be up to 85% more productive than teams made of either humans or robots alone) will be the future of manufacturing.

Preparing a workforce for AI will be an ongoing process, and as technologies evolve, businesses will need to invest in learning and development to ensure that employees remain equipped with the skills necessary to progress.

Start your data journey today

The impact of AI on manufacturing is likely to be substantial, but it’s not a sure-fire route to success without a strategic plan that starts by facilitating reliable data collection methods.

Manufacturers should discuss their requirements with existing solutions providers to discover what data is already available and what solutions can facilitate seamless data collection.

Please visit our blog to learn more about Domino solutions for smart manufacturing and variable data coding.