Industrial Vehicles Components Stress Analysis

Analyses with the purpose of predicting or detecting critical failures of engine components related to unexpected stress and possible overheating.

OVERVIEW

Development of a classification model capable of detecting the vehicles of a fleet for which the breakage of a safety-critical mechanical component of the engine occurred or is going to probably occur in the near future.

Together, a tool for identifying the conditions in which a specific fleet of vehicles may present a problem of overheating of the DPF leading to vehicles failures and, in the more dangerous cases, to fire in order to allow the maintenance intervention and reduce safety risks. The critical conditions have been identified also through the use of pattern extraction based on clustering algorithms.

BENEFITS

  • Reduction of maintenance costs: not all the vehicles involved in the recall campaign need a component replacement, these vehicles can be identified by the check of their data with the results of the developed model.
  • Indications on mitigation actions to be performed: Thanks to the identification of the conditions that may lead to component failures, the manufacturers can extract indications on possible mitigation actions to be adopted in the components/vehicles.

FEATURES

  • Machine learning models: models developed for the objectives achievement are based on machine learning algorithms trained to distinguish the healthy vehicles from the unhealthy ones.
  • Application of systems engineering approach: the activities are performed following the systems engineering approach allowing a deep investigation of the entire system functionalities and not limiting the study to the available data.