XTRACTIS for Civil Engineering

Prediction of Von Mises Maximal Stress in Bridge Pillars

Benchmark vs. Random Forests, Boosted Trees & Neural Networks

Design an AI system that accurately models the constraint in the bridge pillars from several parameters of the bridge and its environment to design, in a rational and explainable way, a bridge supporting a required maximal stress level.
Goals & benefits

Allow domain experts and civil engineers to understand the causal relationships between the bridge structure and environment parameters and the supported constraints in its pillars.

Find the truly influential parameters to anticipate the maximal constraint and thus optimize the structure and construction of the bridge and its pillars.

Deploy a preventive maintenance schedule based on possible changes in environmental conditions.

  • The top-model is a decision system composed of 13 gradual rules without chaining.
  •  Each rule uses from 3 to 9 predictors among the 9 potential predictors that XTRACTIS identified as all significant.
  • Only a few rules are triggered at a time to compute the decision.

It has a good Real Performance (on unknown data).

It computes real-time predictions up to 70,000 decisions/second, offline or online (API).

UC24 scores graph

RFo=Random Forests
BT=Boosted Trees
NN=Neural Networks

Detailed results and explanations in full document

Use Case 2024/03 (v1.0)

Powered by XTRACTIS® REVEAL v13.0.47836 (2024/01)


  1. Problem Definition
  2. XTRACTIS-induced Decision System
  3. XTRACTIS Process
  4. Top-Model Induction
  5. Explained Predictions for 2 unkown cases
  6. Top-Models Benchmark
  7. Appendices