It is vital not to underestimate the importance of AI to manufacturing says a recent report by Accenture. Their study across sixteen industries indicates that amongst those benefiting most will be producers. They forecast that AI in manufacturing will increase corporate profits by an average of 39% by 2035.
AI has the potential to extend across a wide range of manufacturing activities and improve productivity. However, at this early stage of AI, many organizations do not understand the importance of AI to manufacturing, and are unsure of how and when to take their first step.
According to a blog from Schneider Electric, the benefits of AI can include improvements in performance, cost control and processes. Furthermore, it can reduce product cycle development times, and improved efficiency. The value-add of AI also includes 24/7 availability and the capability of machines to learn through experience.
AI will also change the way machine operators perform and help retain the knowledge of skilled workers. New generations entering the industrial workforce will enjoy job enrichment through robotic process automation for repetitive human actions.
AI helps operators to learn and predict tendencies and helps solve complex problems. For example, when managing a process requiring tight control of temperatures, pressures and liquid flows is quite complex and prone to error. Many variables need factoring in to achieve a successful outcome and the human brain alone is unable to cope. AI supported operational decisions help optimise critical factors such as safety, security, efficiency, productivity and even profitability.
Importance of AI to manufacturing
In discrete and process manufacturing, asset maintenance is emerging as one of the early adopters of AI. Organizations are merging the concept of “predictive” maintenance within their more traditional approaches of “preventive” and “break/fix” maintenance. One common example involves a variable speed drive (VSD) connected to a motor.
The intelligence within the VSD gathers data regarding the operation of the motor. On detecting any abnormal behaviours, it flags the motor for either repair or replacement before any failure occurs. Therefore, rather than waiting for scheduled “preventive” maintenance to occur, it supports the prescriptive management of maintenance on a conditional basis. This both reduces cost and increases yield because an asset is only replaced when needed, avoiding any unanticipated downtime.
Similarly, machine learning from edge computing can help in early identification of power generation turbine blade damage, pump feedwater valve problem, plant motor coupling approaching failure and bearing seal differential pressure problem.
A second AI application area combines existing systems and new technologies to control the profitability of the plant operation. By superimposing profit control principles onto process control, a strategy of profitable efficiency emerges.
Real-time accounting (RTA) combines data from the process with financial data to calculate cost and profit points. It is the driver for allowing operators to gain access to profitability data. Thus, algorithms can now help operators make the best decision from both a safety and profitability perspective.
By analysing the problem, technology providers can help to determine whether AI tools can provide a solution to address their problems. Moreover, AI will extend the capabilities of robotics in manufacturing; support machine learning; machine vision, edge computing and predictive maintenance