Acoustic Emission Proof Testing of Insulated Aerial Man Lift Devices


J. of Acoustic Emission, Vol. 18, 2000, pp 224-230

(Initially presented and published at the proceedings of EWGAE 2000 - 24th European Conference on AE Testing, CETIM - France, 24-26 May, 2000, pp. 299-304)

Dr. Athanasios Anastasopoulos, Apostolos Tsimogiannis, Dimitrios Kouroussis


Acoustic Emission (AE) testing of Insulated Aerial Man Lift devices has been proved successful over the years and is widely accepted for testing both new and in-service vehicles. Although testing is relatively easy, data analysis and evaluation is a demanding process, since both metal and composite parts are simultaneously tested, while, the mechanisms used to manipulate the arm movements are potential noise sources. The existing standards, for such type of testing, do not outline pass-fail criteria for each structural part and material, and results evaluation, does basically relies on the experience of the analyst. The results of AE monitoring of five Insulated Aerial Man Lift devises are reported in this work. Data analysis and evaluation is primarily based on multidimensional sorting and unsupervised pattern recognition techniques, which proved efficient for the discrimination of AE sources. Results from various unsupervised algorithms applied either on the AE feature set, or to its principal component projection are discussed. Comparison of the proposed analysis process with traditional data treatment, is presented, as well, Supervised algorithms and Neural Networks were successfully trained, using the unsupervised pattern recognition results, and can be used for the classification of AE data from future tests.