Urgent.News

What's breaking now, across thousands of outlets.

Tech

NEXUS Smart Factory: Predictive Maintenance with Python and Flask

I am Senanur Cetin, the author and maintainer of the NEXUS Smart Factory project. I built this application and published it as an open-source repository at https://github.com/senanurcetin/smart-factory-app . The project focuses on predictive-maintenance analytics, specifically designed for maintenance and reliability teams who need to make data-driven decisions about which assets to inspect…

The NEXUS Smart Factory project is an open-source application developed by Senanur Cetin to address the challenges faced by maintenance teams in industrial environments. The primary focus of the project is predictive maintenance analytics, which aims to prioritize maintenance tasks based on risk assessments derived from sensor telemetry data. This allows teams to make data-driven decisions about which equipment to inspect first, ultimately helping to prevent downtime.

At the core of the NEXUS Smart Factory project is a failure-risk model that processes sensor data from two datasets: the UCI AI4I 2020 dataset and the NASA C-MAPSS dataset. The UCI AI4I 2020 dataset is used for training the failure-risk model, while the NASA C-MAPSS dataset is utilized for a separate remaining-useful-life (RUL) regression study.

By analyzing sensor telemetry data, the model predicts the likelihood of failure for various assets, providing reliability engineers with a ranked maintenance work queue to guide their actions.

The project employs Flask, a Python web framework, to build a plant dashboard that visualizes the ranked maintenance work queue. Instead of displaying raw sensor data, the dashboard presents a ranked list of assets in order of predicted risk level. This allows maintenance teams to quickly identify which equipment requires immediate attention and take appropriate action to avoid potential failures.

In addition to the failure-risk prediction, the NEXUS Smart Factory project also includes a study on Remaining Useful Life (RUL) using the NASA C-MAPSS dataset. This study offers a different perspective on asset health by focusing on the estimated remaining lifespan of the equipment, providing further insights to inform maintenance decisions.

While the NEXUS Smart Factory project offers a functional end-to-end pipeline for predictive maintenance, it does have certain limitations. The application is specifically tailored to the UCI AI4I 2020 and NASA C-MAPSS datasets, making it less suitable for general-purpose data visualization. Additionally, the project is primarily aimed at maintenance and reliability teams and engineers working on portfolios, rather than serving as a tool for broader data analysis.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Content-Addressable Memory vs SRAM Search: Asking Memory to Do the Matching

Most memory answers one question: given an address, return the value stored there. A network switch or a router asks the opposite question: given a value — a destination IP, a MAC address — which…

  • Content-addressable memory (CAM) quickly matches inputs against stored entries in parallel.
  • Static random-access memory (SRAM) requires sequential scans or hashing to find matches.
  • CAM offers instant response but consumes more power and space than SRAM.

WebAssembly vs Containers: Two Kinds of Isolation for Untrusted Code

Running code you did not write is a recurring problem: plugins, serverless functions, user-supplied scripts, third-party dependencies.

  • Containers and WebAssembly (Wasm) restrict untrusted code execution.
  • Containers provide OS-level isolation with resource limits and seccomp.
  • Wasm offers language-level isolation, portability, and smaller trust surface.

More from Friday 20 November →