Disassembler

1. Product Description

1.1. Solution Overview

The AIDEAS Disassembler tool provides industrial machines recycle time and cost saving using a computer vision based technique, made up by an enhanced edge detection algorithm. The model estimates wear state of ended life cycle cutting tools, analyzing a photo, taken at the moment by an operator or stored in a dataset, that depict the superior surface of the tool, and obviously its perimeter. The algorithm, once elaborated the picture, gives back on output which highlights the defects of the tool, measuring its damage level.

1.2. Prerequisites

• Hardware Requirements

The solution requires a camera with a resolution at least 12 MegaPixels, to show particularies of tools perimeters, a clean and clear banket where to take pictures and a device with at least 4 GigaByte Ram to run the algorithm.

• Software Requirements

The algorithm is made up in Python, and at least the 3.9 version is recommended to execute it. The code relies on several libraries, each one for a specific purpose in image processing, data handling and visualization:

  • OpenCV manages image manipulation tasks like contour detection, and picture processing.

  • Pandas is needed for handling data

  • OpenPyXL allows for reading, writing, and modifying Excel output files.

  • NumPy, for numerical computation

  • Matplotlib, for creating visualizations and plots.

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: Not fully developped - under development.

3. Initial Configuration

3.1. First Steps

• Login

To access and utilize the algorithm, users must first log in by selecting the section located in the upper-right corner of the interface and entering their credentials to access the user panel.

LC/DIS Interface

Once the DIS tool have been selected, it will be possible to upload an image of a scraped tool, and, after a few seconds, the results will appear behind.

Results

3.2. Main Workflows

• Workflow Description (Step-by-Step)

The goal of the algorithm is to estimate the remaining life of a weared cutting tool. To achieve this goal using DIS algorithm, firstly the operator takes a picture of the cuttingtool showing the full perimeter of the shape. LC/DIS Interface

Then, the image has to be uploaded through the user interface after logging in. By clicking “Analyze”, the system compares the tool’s shape with reference images. It detects two kinds of defects: erosion (material loss) and protrusion (material deformation). The result appears in a short report, helping the operator decide whether the tool can still be used.

• Examples or Use Cases

In a factory, cutting tools are usually replaced at the end of their estimated life cycle, due to their "limited" cost. This can waste tools that are still usable. Using Aideas Disassembler application, instead, operators can check each tool and keep using those in good condition. For instance, tools used on soft and malleable materials could wear out more slowly. Some tools also wear less depending on their position in the machine. Morevoer, cooling systems and optimized cutting conditions can extend tools life. In all these cases, this algorithm helps to reduce waste and improve efficiency.

4. General Queries

4.1. Installation and Configuration Contact

In the "Information" and "Contact Detailes" sections in the interface it is possible to find more informations about Disassembler - AIDEAS project.

Users can reach support if they need help with installation or configuration via email:

• UNIVPM

  • Tommaso Canullo t.canullo@pm.univpm.it

  • Filippo E. Ciarapica f.e.ciarapica@staff.univpm.it

  • Giovanni Mazzuto g.mazzuto@staff.univpm.it

4.2. Licensing and Support

Users can obtain support through the following channels:

Email Support: Users can contact our support team at the emails listed in 4.1.

Contact AIDEAS: A Box for messages is available for users at https://aideas-project.eu/.

5. Appendices

5.1. Glossary of Terms

AIDEAS : AI Driven Industrial Equipment Product Life Cycle Boosting Agility, Sustainability and Resilience

AI : Artificial Intelligence

DIS : Disassembler

5.2. API Documentation (if applicable)

The solution includes several RESTful API endpoints, implemented using Flask, that support functionalities related to image classification and image uploading to Nextcloud.

[POST]

  • /upload : Uploads a cutting tool image and analyzes it by comparing it with reference shapes.

  • /good_part : Uploads a set of tool images (original, perimeter, area) classified as good to Nextcloud.

  • /damaged_part : Uploads a set of tool images (original, perimeter, area) classified as damaged to Nextcloud.

[GET]

  • /image/ : Returns the processed image as JPEG.

  • /downloads/ : Downloads the image file.