Early research into AI and cognitive computing has already applied real-world solutions to processes. In addition to robotics, additive manufacturing, and other disruptive technologies, the aerospace and defense (A&D) industry has been relatively quick to recognize the potential of AI and readily embrace the science and technology it generates. Both industries have developed and implemented their own digital transformation roadmaps.
Historically, automation systems have been a crucial element of the A&D industry, from the cockpit to the factory floor. We have seen steady progress, from the initial use of autopilots and other automation systems to future autonomous avionics systems. Automated factory production systems have evolved from program-controlled systems to machines and production systems based on predictive, prescriptive, and even autonomous self-healing systems, powered by AI/ML algorithms.
In factory manufacturing, machine learning (ML) is helping to improve and optimize production processes in a variety of ways. These include reducing equipment failure rates to maintain production speeds and minimize costly downtime. Machine learning-based algorithms can access and analyze vast amounts of data from machine vibration sensors to detect and predict machine anomalies and malfunctions. Furthermore, machine learning can prescriptively determine how best to repair and prevent problems. Ultimately, ML algorithms can coordinate a fully self-healing, autonomous production environment for machines and assembly lines.
AI and ML are being used to determine optimal production processes in the aerospace manufacturing industry. Prescriptive analytics, combining big data, mathematical statistics, logic, and machine learning, empirically reveals the root causes of the most complex production problems and then proposes decision-making options for solving them. ML-based intelligent manufacturing systems use pattern recognition techniques to analyze existing production data on products and processes and identify effective (best practices) and ineffective (risky) patterns. These patterns are then translated into human-readable rule forms and applied to manufacturing operations to obtain best practices. Aerospace manufacturers are using this approach to optimize advanced composite material manufacturing processes.
The Rise of Additive Manufacturing
Today, the A&D industry is the largest user of additive manufacturing (AM) parts. From the commercial duopoly of Boeing and Airbus to defense OEMs like Lockheed Martin, thousands of AM “fly-away” parts are used in aircraft manufacturing. For example, Boeing’s latest wind-body model, the 777X, has over 600 printed parts on the aircraft, including over 300 in its massive GE9X engine. It is hailed as the most powerful and efficient engine in today’s twin-jet wide-body aircraft. The Boeing 777X competes with the Airbus A350 XWB in size, performance, and the number of AM parts. The A350 already boasts over 1,000 printed parts.
Boeing's aggressive push into additive manufacturing and its patent applications related to 3D printing for replacing aircraft parts could have a significant impact on the company's future operations. They aim to create a parts library to store AM part definition files, including a database and a parts management system, rather than storing parts in various distribution centers or requiring parts to be shipped to them, which causes substantial delays.
Instead, the company simply extracts specific AM files for the required parts and manufactures them within minutes or hours, provided a printer is available. Currently, the company has over 350 AM standard parts covering 10 different aircraft production programs, and approximately 20,000 printed parts are currently used on its aircraft.
Another A&D manufacturing area where additive manufacturing is having a significant impact is tooling used to support assembly and setup on production lines. Using next-generation large-area additive manufacturing (BAAM) printers, large tooling fixtures and jigs can be manufactured into single large parts in less time, eliminating the need for assembling multiple parts.
Currently, artificial intelligence is an indispensable part of the aerospace additive manufacturing (AM) design process. Achieving the optimal weight-to-strength ratio is a primary goal in aircraft component design, as weight reduction is a crucial factor in fuselage structural design. Today's PLM solutions offer function-driven generative design, using AI-based algorithms to capture functional specifications and generate and validate conceptual shapes best suited for AM manufacturing. This generative functional design approach enables the production of optimal lightweight designs within functional specifications.
