Fabrication Optimiser - FO¶

1. Product Description¶

1.1. Solution Overview¶

The AIDEAS Fabrication Optimiser (AIFO) for scheduling optimisation is a toolkit for calculating the master production plan, the scheduling plan with resource allocation, and for managing production system information. The tool allows production to be planned on different levels and supports production managers through a data-driven approach. Resource allocation, delay and arrival management, capacity scheduling and other aspects are managed via the AI-FO tool’s user interface.

Production Scheduling
Production Planning
Resource Allocation
Manufacturing Information Management

1.2. Features¶

This AIDEAS Fabrication Optimiser offers the following featurs:

Provides the possibility of calculating the production plan in near real time. Scheduling anticipates the allocation of activities to be performed within the constraints of the production site and the allocation of resources to the various tasks.
Provides the ability to calculate the overall production plan through the use of hybrid algorithms, addressing challenges such as material and labour resource allocation and delays in demand fulfilment.
Provides the ability to visualise production plans in tabular form, Gantt charts relating to production orders and Gantt charts relating to allocated resources. Tables and diagrams are interactive with the possibility to edit, download and print information.
Provides the possibility of adapting the information in the management databases to the designated data model. This is done via a converter that takes information from different sources and returns a json or xlsx file to be uploaded to the platform. Information regarding the data model present in the following publication (https://doi.org/10.1016/j.compind.2021.103398)
Provides a section for visualising and managing production data.

• Technical Specifications¶

The tool exploits Deep Reinforcement Learning models for production order scheduling and linear programming models mixed with erutistic and metaheuristic algorithms for master production planning. The models optimise a multi-objective function that optimises makespan values, delivery delays and operator utilisation rates. Should there be a need for several target functions, there will be a need to re-train the models. The backend of the AI-FO is developed using python and FLASK as the framework for the API server. The backend provides the API endpoints with which the frontend can communicate to, send requests, and obtain the results.
The frontend of the solution is developed in REACT.
For deployment, docker is used since it is the most widely used containerization solution. Docker also makes it easy to deploy the packaged application into the runtime environment and is widely supported by deployment tools and technologies.

• Technical Development¶

This AIDEAS Solution has the following development requirements:

Development Language: Python and Javascript.
Libraries: Numpy, Pandas, Scikit-Learn, PyTorch, Flask, gymnasium, Ray, rrlib, pyomo, plotly
Container and Orchestration: Docker, Kubernetes.
User Interface: React, PrimeReact.
Application Interfaces: RestAPI.

• Hardware Requirements¶

AI-FO can run on any platform that supports Docker containers.

• Software Requirements¶

Docker Desktop (Windows, Mac, or Linux)
Python
npm (for frontend deployment)

2. Installation¶

2.1. Environment Preparation¶

Ensure that all dependencies, including Docker, Python, and npm, are installed. Clone the repository from the official GitLab project and configure the backend and frontend environments as needed.

2.2. Step-by-Step Installation Process¶

Local Installation: Requires configuring backend and frontend, installing dependencies, and launching services manually.
Docker Installation: Uses a docker-compose.yml file to deploy the application.
Kubernetes Installation: Pending implementation.

3. Initial Configuration¶

3.1. First Steps¶

HOME¶

Dashboard → Tab in which an introduction of AIFO is displayed and from which the other tabs can be accessed too.
Help → Tab with guidelines.

AI-FO¶

Scheduling Plan → Tab where you can upload data, see the last calculated scheduling plan, edit it, consult gantt diagrams, add new orders and calculate a new scheduling plan.
Production Plan → Tab where you can upload data, alculate the production plan, save it and download it.
Production Data →Tab where it is possible to view and edit various useful information for production management such as: list of machines in the catalogue, list of available operators, types of workstations available, availability of operators according to calendar, production times and production constraints, assembly sequences for each product.

4. General Queries¶

4.1. Installation and Configuration Contact (If Service Provided)¶

For installation and configuration support, users should refer to the official GitLab project or the associated organization:

UNIVPM: Mateo Del Gallo (m.delgallo@pm.univpm.it) Filippo Emanuele Ciarapica (f.e.ciarapica@staff.univpm.it) Giovanni Mazzuto (g.mazzuto@staff.univpm.it)
UPV: Juan Pablo Fiesco Muñoz (jfiesco@cigip.upv.es) Miguel Angel mateo Casali (mmateo@cigip.upv.es) Beatriz Andrés Navarro (bandres@cigip.upv.es)
ITI: Diego Silveira Madrid (dsilveira@iti.es)

4.2. Licensing and Support¶

Users can contact our support team at the emails listed in 4.1. section for assistance
Pricing and licensing details are available upon request.

Subject	Value
Payment Model	Quotation under request
Price	Quotation under request

5. Appendices¶

5.1. Glossary of Terms¶

AIDEAS: AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience
AI: Artificial Intelligence
AI-FO: AIDEAS Fabrication Optimiser

5.2. API Documentation (if applicable)¶

By default, the backend server is served on port 5002 and allows the following API methods. These methods are accessible through the application frontend, or by sending the proper request using tools like Postman, or directly with Python code.

Resource	GET	POST
`/sync`		Supported
`/upload`		Supported
`/SchedTable`		Supported
`/newOrder`		Supported
`/process_data`		Supported
`/result`		Supported
`/download_result`	Supported

5.3. Console Commands List (if applicable)¶

npm install for frontend dependencies.
pip install -r requirements.txt for backend dependencies.
docker-compose up --build for Docker-based deployment.
python Import_data_services.py to launch the backend server.
npm run dev to start the frontend server.