Skip to main content

A software package for the integration of metrological input into an agent-based system for the consideration of measurement uncertainty in current industrial manufacturing processes.

Project description

CircleCI Documentation Status Codecov Badge

Multi-Agent System for Metrology for Factory of the Future (Met4FoF) Code

This is supported by European Metrology Programme for Innovation and Research (EMPIR) under the project Metrology for the Factory of the Future (Met4FoF), project number 17IND12. (https://www.ptb.de/empir2018/met4fof/home/)

About

  • How can metrological input be incorporated into an agent-based system for addressing uncertainty of machine learning in future manufacturing?
  • Includes agent-based simulation and implementation
  • Readthedocs documentation is available at (https://agentmet4fof.readthedocs.io)

Use agentMET4FOF

The easiest way to get started with agentMET4FOF is navigating to the folder in which you want to create a virtual Python environment (venv), create one based on Python 3.6 or later, activate it, first install numpy, then install agentMET4FOF from PyPI.org and then work through the tutorials or examples. To do this, issue the following commands on your Shell:

$ cd /LOCAL/PATH/TO/ENVS
$ python3 -m venv agentMET4FOF_venv
$ source agentMET4FOF_venv/bin/activate
(agentMET4FOF_venv) $ pip install agentMET4FOF
Collecting agentMET4FOF
...
Successfully installed agentMET4FOF-... ...
(agentMET4FOF_venv) $ python
Python ... (default, ..., ...) 
[GCC ...] on ...
Type "help", "copyright", "credits" or "license" for more information.
>>> from agentMET4FOF_tutorials import tutorial_1_generator_agent
>>> tutorial_1_generator_agent.demonstrate_generator_agent_use()
Starting NameServer...
Broadcast server running on 0.0.0.0:9091
NS running on 127.0.0.1:3333 (127.0.0.1)
URI = PYRO:Pyro.NameServer@127.0.0.1:3333
INFO [2020-02-21 19:04:26.961014] (AgentController): INITIALIZED
INFO [2020-02-21 19:04:27.032258] (Logger): INITIALIZED
 * Serving Flask app "agentMET4FOF.dashboard.Dashboard" (lazy loading)
 * Environment: production
   WARNING: This is a development server. Do not use it in a production deployment.
   Use a production WSGI server instead.
 * Debug mode: off
 * Running on http://127.0.0.1:8050/ (Press CTRL+C to quit)
...

Now you can visit http://127.0.0.1:8050/ with any Browser and watch the SineGenerator agent you just spawned.

To get some insights and really get going please visit agentMET4FOF.readthedocs.io .

Get started developing

First clone the repository to your local machine as described here. To get started with your present Anaconda installation just go to Anaconda prompt, navigate to your local clone

cd /LOCAL/PATH/TO/agentMET4FOF

and execute

conda env create --file environment.yml 

This will create an Anaconda virtual environment with all dependencies satisfied. If you don't have Anaconda installed already follow this guide first, then create the virtual environment as stated above and then proceed.

Alternatively, for non-conda environments, you can install the dependencies using pip

pip install -r requirements.txt

First take a look at the tutorials and examples or start hacking if you already are familiar with agentMET4FOF and want to customize your agents' network.

Alternatively, watch the tutorial webinar here

Updates

  • Implemented base class AgentMET4FOF with built-in agent classes DataStreamAgent, MonitorAgent
  • Implemented class AgentNetwork to start or connect to a agent server
  • Implemented with ZEMA prognosis of Electromechanical cylinder data set as use case DOI
  • Implemented interactive web application with user interface

Screenshot of web visualization

Web Screenshot

Note

  • In the event of agents not terminating cleanly, run

    taskkill /f /im python.exe /t
    

    in Windows Command Prompt to terminate all background python processes.

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

agentMET4FOF-0.1.10.tar.gz (33.4 kB view hashes)

Uploaded Source

Built Distribution

agentMET4FOF-0.1.10-py3-none-any.whl (36.5 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page