ezzaimaaa/jesa-rbmi-inspection

JESA RBMI Inspection — Dynamic Inspection Frequency (PFE)

Gradio application for Risk-Based Maintenance Inspection (RBMI) at JESA (Jorf Lasfar).

Built by: El Mehdi Ezzaim — Final Year Industrial Engineering Student, ENSA El Jadida. Internship: JESA (Jacobs Engineering SA), Jorf Lasfar, Morocco.

What it does

• Calculates Remaining Life Assessment (RLA) and Risk-Based Maintenance Inspection (RBMI) dynamically.
• Compares Fixed JESA inspection plan vs Dynamic RBMI plan with cost savings.
• Recommends CND (Non-Destructive Testing) methods and corrective actions.
• Shows regression chart with alert when predicted failure crosses FFS limit.

Standards

• JESA ST-RBMI-02-OIJ 2023
• API 580 (RBMI Framework)
• API 510 (Pressure Vessels)
• API 653 (Storage Tanks)
• ASME Section VIII Division 1 UG-27

Equipment Covered

• 401AAF01 — Sulfuric acid duct
• 401AAD03 — Final duct
• 412AAR01 — Tank T1 zone
• 412ABR01 — Tank normal zone
• 401AAR09 — Air reservoir

Input

• Equipment TAG
• Measured UT thickness (mm)
• Inspection date

Output

• RLA (years)
• Status with color: 🔴 Critical, 🟠 Surveillance, 🟡 Attention, 🟢 OK
• Dynamic inspection frequency
• Predicted year of failure
• Regression chart (thickness vs time)
• Cost comparison: Fixed vs Dynamic

Generated by ML Intern

This model repository was generated by ML Intern, an agent for machine learning research and development on the Hugging Face Hub.

• Try ML Intern: https://smolagents-ml-intern.hf.space
• Source code: https://github.com/huggingface/ml-intern

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ezzaimaaa/jesa-rbmi-inspection"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

For non-causal architectures, replace AutoModelForCausalLM with the appropriate AutoModel class.