MLPro-MPPS - A Customizable Multi-Purpose Production System in Python
Project description
MLPro-MPPS - A Customizable Framework for Multi-Purpose Production Systems in Python
MLPro-MPPS provides functionalities to design and develop customizable multi-purpose production systems in Python. This framework is integrated with MLPro (https://mlpro.readthedocs.io) and inherits several basic functionalities from MLPro. The user can design a production system simulation from the lowest component level (sensors and actuators) until the combination of them in the form of MPPS. The other possibility is to use the ready-to-use components in the pool of objects. Moreover, since MLPro-MPPS is compatible with MLPro, it is possible to utilize MLPro-MPPS as an environment in MLPro-RL, as a game board in MLPro-GT, or as a state transition function in an MLPro-BF-Systems. Hence, MLPro-MPPS is reusable and powerful.Getting Started
To get started with MLPro-MPPS, you can begin with the following tasks:
Installation from PyPI
pip install mlpro-mpps
Dependencies
Please read requirements.txt
Introduction Video
You can see a video of the introduction of MLPro-MPPS at the 2nd IEEE Industrial Electronics Society Annual Online Conference by clicking this link.
First Steps
After installing MLPro-MPPS and its dependencies, we suggest starting with the ready-to-run examples:
- HOWTO 001 - SETTING UP COMPONENTS AND MODULES
- HOWTO 002 - SETTING UP MPPS
- HOWTO 003 - MPPS IN REINFORCEMENT LEARNING
- HOWTO 004 - MPPS IN GAME THEORY
Additionally, the class diagram of the basic function is available in this directory. The ready-to-use components and MPPS samples can be found in this directory.
Key Features and Functionalities
a) Providing base classes of components in a clean structure
- Including base classes for a sensor, an actuator, and a component state (required for simulation)
b) Versatile and configurable
- MPPS is versatile, which means that it has a high degree of flexibility, where the users can set up a production system with as many sensors, actuators, components, and modules as possible
- Moreover, MPPS is also not restricted to a modular production system, but also applicable in any form of technical systems
c) Simplification of measurements and designs of the MPPS-based systems' dynamics
- When MPPS is simulated, the dynamics of the sensors and component states are affected by the actual status of the actuators. In the simulation mode, their dynamics are measured through a mathematical calculation that is defined by the TransferFunction class of MLPro
- The mathematical calculation can be attached to the lowest level of the components, such as sensors and component states, which make them reusable and reproducible.
d) Well-integrated to MLPro
- Possibility to convert MPPS into the reinforcement learning environment in MLPro-RL or game theory game board in MLPro-GT
- Possibility to reuse functionalities from MLPro
Development
- Consequent object-oriented design and programming (OOD/OOP)
- Quality assurance by test-driven development
- Hosted and managed on GitHub
- Agile CI/CD approach with automated test and deployment
- Clean code paradigma
Citing MLPro-MPPS
Project and Team
Project MLPro-MPPS was started in 2022 by the Group for Automation Technology and Learning Systems at the South Westphalia University of Applied Sciences, Germany.
MLPro is currently designed and developed by Steve Yuwono, Marlon Löppenberg, and further contributors.
How to contribute
If you want to contribute, please read CONTRIBUTING.md
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for mlpro_mpps-1.2.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 21572b13812b70f43dd2474cf402c56f3b31e35ab6325fb4ceed16d0165fe1aa |
|
MD5 | 1f0d4c6e68c0154a6b1fcf50f793bd60 |
|
BLAKE2b-256 | 6e66568a0648ac6e2a9d9c453d4864b88fde194dfe8fa8d5563b5bb0753175d7 |