Diagnostic
Engineer

AI-assisted technical diagnostics system that reduces uncertainty and turns every experience into permanent knowledge.

Why NG?

Every feature designed to make your field diagnostics faster, smarter, and permanent.

Iterative diagnosis

Reduce uncertainty

Living knowledge

Learn and retain knowledge

Always on

Available 24/7

Operational impact

Reduce NPT & downtime

See NG in action

One minute of real demo footage. No editing, just the system running.

About the Creator

Elkin Mora

Electromechanical Engineer, MSc in Industrial Control. 15+ years in oil & gas drilling — PLC/DCS, SCADA/HMI, VFDs, and root cause analysis. NG was born from the conviction that no company should pay twice for the same lesson.

MATLAB/Simulink PLC/DCS Python SCADA/HMI

Elkin Mora

Control Engineer & Developer

✉ ingelkinmora@gmail.com
Published Paper

Real-Time Monitoring System for Mast Hoisting

A distributed monitoring architecture that simultaneously tracks hydraulic pressure and angular inclination during mast hoisting in drilling rigs equipped with mechanically coupled three-stage telescopic hydraulic cylinders. The system detects critical stage transitions and operational deviations in real time, defining alarm thresholds that empower operators to make informed, safety-driven decisions in the field. Validated on structures exceeding 40 tonnes with proportional valve control. It establishes the foundation for fault-tolerant control, predictive maintenance, and synchronization safety in multi-actuator hydraulic systems applied to oil and gas drilling operations.

Research Project

Digital Twin & Fault-Tolerant Control Architecture

A field-validated digital twin of a drilling rig mast raising system with mechanically coupled multi-stage telescopic hydraulic cylinders, built in MATLAB/Simulink to study the structural observability limits of position-based synchronization controllers. The research characterized 77 fault scenarios across three structural classes (compensable, detectable, invisible) and demonstrated that differential pressure is 25–140× more sensitive than position for anomaly detection. The proposed three-layer fault-tolerant control architecture combines Sliding Mode Control (SMC) for cylinder synchronization, RBF Neural Networks for 7-class fault classification (93.8% accuracy), and a Mamdani Fuzzy Supervisor for autonomous decision-making — achieving internal seal leak detection in 60 seconds with zero false positives.

Ready to transform your field diagnostics?

Let's talk about how NG can help your operation reduce uncertainty and retain knowledge.

✉ contact@engi.solutions