Prediction and Optimization Designer

The PO Designer in ZDMP supports the development of process quality solutions using Python by enabling the discovery and reuse of open-source resources. It provides a search engine based on taxonomies extracted from the Zero Defects Manufacturing Vocabulary, allowing data scientists to easily find and clone resources for their development projects. Key concepts include layers representing specific algorithms or machine learning models, datasets for problem instantiation, and development projects with pre-configured files for deploying and running algorithms as PO Runtime components.

Benefits

  • Find Open-source modules that can be used to develop new runtime components (simulation, prediction, detection, or optimisation) for process quality assurance using natural language queries
  • Find open source templates you can reuse to develop new Python analytical components, implementing sample metadata (ie manifest files), and all the Continuous Integration / Continuous Development (CI/CD) needed to deploy and run an algorithm as a runtime component

  • Share open-source projects with the ZDMP developer community

Play Video

Find Prediction and Optimisation Projects

The PO Designer offers a search engine for browsing and filtering analytical models based on a zero-defect manufacturing taxonomy. Supported by the ZDM ontology, it provides a unified approach to finding datasets and algorithms related to process and product quality. By labeling challenges and solutions with ontology classes, users can accurately describe their use cases and discover suitable solutions.

Develop Prediction and Optimisation Projects

Prediction and optimization models and datasets are essential for Prediction and Optimization Projects. Developers can add new layers to the Designer, allowing other developers to utilize them. Models must adhere to certain specifications and include necessary files and folders for proper indexing and reusability. Template projects provided in the Designer meet these requirements, reducing concerns for data scientists, while still providing flexibility for file structure modifications if necessary.

Register a Resource

In the context of the Register Resource Page, developers have access to a user-friendly form that facilitates the indexing of a new resource within the taxonomy. This page presents several fields that developers can fill out to provide the necessary information about the resource.

developers contribute to the expansion and organization of the taxonomy, making it easier for others to discover, utilize, and collaborate on resources within the system.

Manage your Resources

The page “My Resources” lists the resources that an organisation has indexed in the search engine. The design is similar to the My Projects Page. The dashboard shows the list of resources published by an organisation. If the Details button besides the name is clicked (magnifier icon), the detailed information is loaded into the Resource Details panel to the right.

Additional ressources

Learn more about i4FS by visting the project website for general information, the wiki for information about the core components, the Technical Manual for API documentation, and downloading the repository’s source code.

Training Academy

Get a better understanding of the global architecture and information flow.

Source code

Our source code is opensource and available on our Gitlab repository.

Software Documentation

Read our easy to follow documentation to learn how to use the i4 Components.