Share

Innovation in machine learning for electrical cable diagnostics wins award at AUTOTESTCON

Best Paper Award ceremony by Michael Seavey (Technical Program Chair) and Bob Rassa (Chair) at the IEEE AUTOTESTCON conference. © J. Reisman/AUTOTESTCON
CEA-List received the Best Paper Award at IEEE AUTOTESTCON, an international automated testing event for military and aerospace decisionmakers. An innovation in accurate, low-cost electrical cable diagnostics won the award, marking a major step towards more effective and affordable preventive maintenance.

Reconstructing compressed OMTDR (Orthogonal Multi-tone Time Domain Reflectometry) data is a challenge that CEA-List is addressing through new machine-learning-based approaches that make it possible to diagnose faults from the compressed data—with no reconstruction needed.

To diagnose a fault, it must first be detected (by estimating the impedance) and then located (by estimating the position). Here, the estimations required for this two-step process are generated by the KNN (K-nearest neighbors) algorithm and a CNN (convolutional neural network).

 


Classic reflectometry architecture and compressed reflectometry acquisition architecture. © H.Slimani/CEA


 

This eliminates the need for complex, iterative reconstruction algorithms—and puts new reflectometry architectures tailored to the low-latency and real-time processing requirements of embedded systems within reach. Both the impedance estimation and fault location results were excellent in terms of accuracy. The CNN was shown to excel at estimating impedance, while the KNN algorithm showed its strengths at fault location. The requirements of each use case—available resources, required accuracy, the amount of noise—will condition which model is best. The research also produced promising fault location results with high compression factors. The award confirms AI’s potential for processing compressed data directly in cable fault diagnosis use cases.

 


Example of simulated measurements of compressed acquisition of OMTDR reflectometry data for different types of defects and faults. © H.Slimani/CEA


 

Patent

One patent was filed for the diagnosis of faults in electrical cables using machine learning and reflectometry methods.

 

Flagship publications

AI can take over when compressed signals get too complex, instantly revealing hidden defects and faults in electrical cables.

Rebecca Cabean

Hanane Slimani

PhD candidate — CEA-List