LaserSense AI: Intelligent Laser Cutting Optimization Platform (NexCut)

Introduction

Tech Stack

React.js

Python FastAPI

PostgreSQL

RAEM 1 Sensor Integration

AI Parameter Suggestion Model

Basecamp

QA Testing

Challenges

1. Manual Parameter Selection

   Operators needed to manually determine cutting parameters such as speed, focus, gas pressure, nozzle type, machine power, frequency, and duty cycle based on material and job conditions.

2. Inconsistent Cutting Quality

   Variations in material type, grade, thickness, and machine conditions could result in inconsistent edge quality, scrap risk, and production inefficiencies.

3. Limited Visibility Into Test Cut Performance

   Operators lacked a clear way to review sensor data, compare original and optimized settings, and understand the effect of AI adjustments before final production.

4. Lack of Centralized Machine and Material Configuration

   Machine specifications, material grades, and predefined optimized parameters needed to be managed centrally to support repeatable and consistent cutting operations.

Key Features

AI-Powered Cutting Parameter Suggestions

Recommends optimized values for cutting speed, focus, gas pressure, nozzle type, machine power, frequency, and duty cycle based on material, thickness, machine configuration, operating mode, and sensor inputs.

Guided Job Configuration Workflow

Provides operators with a structured setup process covering material selection, material condition, cutting or piercing mode, operating type, test cut, and final production settings.

Sensor-Based Test Cut Analysis

Captures and displays live RAEM 1 sensor values during test cuts, helping operators evaluate machine behavior and cutting performance before full production.

AI Adjustment Logs and Parameter Comparison

Shows the difference between initial operator settings and AI-optimized parameters, along with adjustment history, confidence levels, and recommended changes.

Cut Quality and Scrap Risk Evaluation

Provides visibility into edge quality, cutting quality, confidence score, and scrap risk, enabling operators to validate settings before starting final production.

Centralized Machine, Material, and Parameter Management

Allows administrators to manage machine specifications, material types, grades, thicknesses, and predefined optimized parameters for consistent and repeatable workflows.

Results & Impact

The platform improved laser cutting operations by reducing dependency on manual parameter tuning and repetitive setup processes. AI-assisted recommendations and real-time sensor insights enabled operators to validate configurations faster, reduce material wastage, and achieve more consistent cutting quality across different machines, materials, and job conditions. Centralized parameter management also simplified repeat production workflows and reduced overall setup effort.

LaserSense AI successfully transformed traditional laser cutting preparation into an intelligent, sensor-driven, and data-supported optimization workflow. By combining AI-powered parameter recommendations, live sensor analysis, test cut validation, cutting quality assessment, and centralized configuration management, the platform established a scalable foundation for improving manufacturing consistency, reducing operational inefficiencies, and supporting long-term production optimization.

Visit Portfolio