This Case Shows Specific Expertise. Find the Companies with the Skills Your Project Demands!

You're viewing one of tens of thousands of real cases compiled on Many.dev. Each case demonstrates specific, tangible expertise.

But how do you find the company that possesses the exact skills and experience needed for your project? Forget generic filters!

Our unique AI system allows you to describe your project in your own words and instantly get a list of companies that have already successfully applied that precise expertise in similar projects.

Create a free account to unlock powerful AI-powered search and connect with companies whose expertise directly matches your project's requirements.

AI-Driven Optimization of Crude Oil Distillation Units Using Reinforcement Learning

tooploox.com

Energy & natural resources

Information technology

Manufacturing

Manual Management of Crude Oil Distillation Units Leading to Inefficiencies

Current manual operation of Crude Oil Distillation Units (CDUs) results in suboptimal scheduling, increased risk of production interruptions, and excessive operator workload. Challenges include managing unpredictable tanker arrivals, optimizing oil flow between tanks and CDUs, and maximizing profitability through dynamic crude oil allocation.

About the Client

A leading provider of industrial software solutions specializing in CAD and process optimization for heavy industries, with expertise in oil and gas sector automation.

Automation and Optimization of CDU Workflow

Develop reinforcement learning-based agents for dynamic scheduling of oil flow
Create a high-fidelity refinery simulator for safe AI training
Reduce manual intervention while maintaining continuous CDU operation
Maximize refinery profitability through optimized crude oil allocation
Improve resilience to supply chain uncertainties (e.g., tanker delays)

Core System Functionalities

Real-time refinery process simulation environment
Reinforcement learning agents for Berth and CDU management
Dynamic scheduling optimization with constraint handling
Production bottleneck prediction and mitigation
Integration with IoT sensor data for real-time monitoring

Technology Stack

Reinforcement Learning (TensorFlow/PyTorch)

Python-based simulation framework

Industrial IoT protocols (OPC UA, MQTT)

Containerized microservices architecture

Cloud-based training environment

System Integrations

Existing SCADA systems for CDU control
Tank level sensor networks
Tanker arrival tracking systems
Refinery production planning software

Non-Functional Requirements

99.99% system availability for critical components
Real-time decision-making latency <50ms
Support for 1000+ concurrent sensor data streams
Role-based access control for operational security
Fault-tolerant architecture with rollback capabilities

Business Impact

Expected 20-30% increase in CDU operational efficiency, 40% reduction in production interruptions, and $2-5M annual cost savings per installation. Reduced operator workload by 60% through automated decision-making while maintaining safety margins and improving response to supply chain disruptions.