How AI and machine learning are reshaping the manufacturing sector
Jan. 12, 2018 - The world is rapidly moving toward Industry 4.0 or the Fourth Industrial Revolution, where artificial intelligence (AI) and machine-learning based systems are not only changing the ways we interact with information and computers but also revolutionizing the manufacturing sector.
According to a new AI report from Infosys, in the manufacturing and high tech sector specifically, use of machine learning is higher (79 per cent) as is the institutionalization of enterprise knowledge using AI (66 per cent) and cognitive AI-led processes/tasks (60 per cent). Most companies want to automate manufacturing to increase productivity (66 per cent), minimize manual errors (61 per cent), reduce costs (59 per cent) and refocus people’s efforts on non-repetitive tasks that benefit from human intervention (50 per cent).
The increasing demand for customized products at reasonable rates is the principal driving force behind the need to use various aspects of AI and machine learning in the manufacturing process. Here is how these disruptive technologies are affecting manufacturing now and in coming years.
1. Predictive maintenance for reducing O&M costs
Even today, most manufacturing plants have a fixed schedule for preventive maintenance. However, as it takes place regardless of the operating conditions, this type of preventive maintenance often leads to unexpected equipment downtime, wasted labour, and production losses. With the help of cognitive AI technology, smart sensors, and an interconnected network of machines, plant engineers will able to monitor the devices on the floor. The constant monitoring will, in turn, allow floor managers to generate predictive analytics.
For years, Digital Twin technology has been restricted to high-end applications such as running spacecraft simulations at NASA. However, the rapid rise of AI and allied technologies are bringing this technology to the manufacturing sector. It can analyze the data collected from a complex array of sensors. It can be used to track anomalies and diagnose failure situations. Gartner predicts that by 2021, half of the large industrial companies will use digital twins, resulting in those organizations gaining a 10 per cent improvement in effectiveness.
Companies around the globe are trying to reduce equipment downtime using various AI technologies. GE built its first-ever Brilliant Factory in Pune, India, powered by Predix, an Industrial Internet of Things (IIoT) platform. The platform uses sensors for monitoring each step of the manufacturing process automatically to prevent downtime. The company claims the technology improved equipment effectiveness at this plant by 18 per cent.
2. Improved supply chain management
In the recent years, several companies have started using AI and machine learning to optimize global supply chain management. The modern supply chains generate massive amounts of data. AI not only helps to analyze this data but also organize it into useful bits and pieces. With the help of AI, it becomes easier to adapt to changing market scenarios.
In fact, several different tech companies have developed customized AI-based supply chain management solutions as software as a service (SaaS). For example, IBM’s Watson Supply Chain system uses cognitive AI technology to monitor supply chain process. It collects and analyzes data from different sources including social media, news feeds, weather forecasts and historical data. TransVoyant can also collect and analyze nearly one trillion events from sensors, satellites, radar, video cameras and smartphones daily.
In the end, the use of AI and machine learning boils down to creating a cohesive and self-sustaining ecosystem that facilitates seamless exchange of information. So, it will enhance the performance across all areas of a supply chain including warehousing, transportation, customer feedback, production, and packaging.
3. Seamless quality control
AI or machine-learning based quality assurance has become the new research frontier in the manufacturing sector. Until now, most manufacturing companies have used a network of computers and sensors to remove low-quality products from the assembly line. However, AI and machine-learning based system will provide a seamless quality control over the entire manufacturing process.
Rather than relying on in-process manual inspections, manufacturers can use computers and sensors that can discover defects with striking efficiency and accuracy. It will enable companies to improve the features of low-quality products instead of discarding them. It helps reduce expensive production delays that continue to pile in conventional quality control systems. As a result, the demand for human labour in quality control is more likely to dwindle in future.
4. Improved human-robot collaboration
With the rise of AI and machine learning, the era of dumb robots engaged in repetitive manufacturing tasks is coming to an end. In future, humans and robots will need to work together to create agile manufacturing processes. Working with the heavy duty dumb robots is still considered a risk factor in most manufacturing industries. However, working with next-generation smart robots will be much safer and manageable for the human workforce.
KUKA, the Chinese-owned German manufacturing company, says it has developed the world’s first series-produced and HRC-compatible smart robot called LBR iiwa. It can work directly with its human colleagues without compromising their safety. Such robots have virtually endless applications in the coming years. They can improve efficiency and flexibility in factories as you can reassign any task to them. They will also be able to recognize patterns and learn to modify their response accordingly.
5. Consumer-centric production
Consumerism has come a long way. Today, manufacturers need to focus on consumer-centric production as the demand for highly customized products is on the rise. This is where AI and machine learning come in. These technologies will allow companies to build smart manufacturing processes that can adapt to the ever-changing consumer demand.
However, it will require a comprehensive network that connects consumers directly with manufacturers. One of the best ways to make this happen is to connect IoT with IIoT. For example, companies can collect data from smart homes to understand the latest consumer trends. These technologies will usher in a new level of communications in the modern manufacturing industry.
AI and machine learning are the backbones of Industry 4.0. The deployment of cutting-edge AI and machine learning technologies will cause massive disruption in the manufacturing sectors, and has already helped automate core manufacturing processes.
Jack Warner is a tech enthusiast who loves to explore the world of machines and automation. He currently writes for Power Jack Motion.
ATS Knowledge Day
March 28, 2019
Hannover Messe 2019
April 1-5, 2019
RFID Journal LIVE!
April 2-4, 2019
April 8-11, 2019
2019 Annual Valve Industry Knowledge Forum
April 9-11, 2019
Advanced Design & Manufacturing (ADM) Canada
June 4-6, 2019