SOPRENE Programme Brings ‘Unsupervised’ AI to Practicable Levels
Indra and the Spanish Navy have tested one of the world’s first artificial intelligence (AI) systems with the capacity to learn by itself and take decisions as if it were human, the company announced on 17 September.
The demonstrator has been designed to predict malfunctions and improve maintenance and availability in the Spanish Navy’s fleet. This is one of the first solutions that applies what is termed ‘unsupervised’ AI, hitherto restricted mainly to academic research, bringing it from an experimental to a practical environment.
This type of intelligence differs from the supervised variety in that, instead of learning a procedure to be followed to solve a given problem, the machine learns to detect the problems and apply the logical operations that any computer might employ to reach a solution by its own means, without human assistance or having to be told how to do it.
In the case of the SOPRENE Project, Indra engineers taught the system to understand how the engines of F100 frigates and BAM OPVs work, providing it with an enormous amount of detail and precision. With this information, the system was capable of detecting deviations in normal operations and predicted the engine trouble and malfunctions that the vessels had over the last five years.
To perform the tests and verify the accuracy of the results, Indra used the data records stored by the Spanish Navy’s Data Monitoring and Analysis Center (CESADAR) in Cartagena, a leading authority in Spain in the use of mechanical malfunction prediction techniques, which has promoted and led the technology side of the SOPRENE Project in the Spanish Navy since 2018.
The potential for non-monitored technology is much greater than the supervised variety, and offers many advantages for the maintenance of next-generation vessels:
• It is a system capable of attaining results that are neither predefined or known a priori: this allows it to learn from successes and mistakes, as a human would, to achieve ever greater efficiency and speed;
• It is a universal system: developed to check the functioning of the F100 frigate and OPV engines, but can be easily adapted to monitor other systems on these vessels or others, and even be brought into other defence or civilian fields;
• It does not require the past performance records of a system to be trained. It can thus overcome one of the toughest barriers that prevent conventional AI systems from predicting malfunctions that a newly developed vessel will experience, one that has not yet been at sea;
• The system can detect the most serious engine failures: for the same reason as above, the system can detect failures that have never occurred and cannot be replicated intentionally, because it would be too costly or even catastrophic for the vessel. These types of malfunctions are the most unlikely but also the most important, as they can endanger the crew.
With this project, Indra and the Navy are at the cutting edge of AI R&D for solutions of this kind. For the Navy, use of this technology means a major operational advantage, as it can plan its missions with greater precision and bring forward or postpone repairs as needed. As for Indra, it bolsters its leadership position in a field of knowledge that will transform all areas of technology.