Cookie Consent by PrivacyPolicies.com
Quality Automation with AI and Relimetrics

Knowledge Hub

Explore & Learn ReliVision with Proven Use Cases

ReliWeb

ReliAudit is the edge module that runs your inspection solutions on the shop floor. ReliWeb is the browser interface onto it — where operators review individual results, read the statistics, and accept or dispute what the AI decided.

The web-based HMI

Reviewing results in ReliWeb

The user can monitor individual audit and inspection results, provide feedback by accepting or disputing results, and review audit statistics using ReliWeb, a web-based HMI. ReliWeb has two main parts to provide these functionalities: the Audit History tab and the Audit Analytics tab. The former is for individual audit and inspection review, the latter for retrospective statistical analysis — trends as a function of time and audit outcome.

ReliWeb · part 1

Audit History

  1. The “Audit History” page displays the audit outcomes conducted by the AI solutions, allowing the user to see the quality check and inspection results in real time.

    The ReliWeb Audit History page listing audit outcomes in real time
  2. The user can type in the “Search Serial Number” (1) area to view the results, and use the “Select Option” (2) filter to customize the audit results display based on specific preferences.

    Serial number search field and the Select Option filter on the Audit History page
  3. Once an audit is selected, click the “Load” button to generate and display the audit results in detail. Please note that loading an audit can take a few minutes. Once loading is completed, the results will be ready for review.

    Load button used to open the selected audit in detail
  4. The “Clear” button allows users to delete the selected audit. Once clicked, the current audit will change to “None”.

    Clear button resetting the selected audit to None
  5. Audit results can be checked from the “Audit Results” column.

    The Audit Results column showing the outcome of each audit
  6. Filters can be used to quickly view NOK, OK and Others audit results, or to display results within a specific time period.

    Filters for NOK, OK and Others results and for a time period
  7. To review any audit in detail, click on the result. On the detail page, the user can view a comprehensive breakdown of the audit results, highlighting areas of interest such as detected defects (1), showing or hiding annotations (2), and zooming in on the detected components (3).

    Audit detail view with detected defects, annotation toggle and zoom
  8. The user can dispute the audit results by clicking the “Dispute” check box. Audit results that are not disputed will be considered accepted. This feedback loop is vital for refining the AI models and adapting to changing production conditions.

    Dispute check box on an individual audit result
  9. Located at the bottom of the page, the “Accept All” and “Dispute All” controls enable operators to accept or reject every result on screen at once. Additionally, if an operator corrects a defective (NOK) sample on the spot, they can use the “Fixed It” button.

    Accept All, Dispute All and Fixed It controls at the bottom of the page
  10. Click on the “Back” icon to go back to the Audit History page.

    Back icon returning to the Audit History list
Watch the video: Audit History

ReliWeb · part 2

Audit Analytics

  1. The “Audit Analytics” tab tracks total audit counts across defined timeframes, including date and hour breakdowns, enabling users to evaluate peak activity, evaluate trends, and recognize patterns. To filter results, select the preferred timeframe (1) and click “Refresh Analytics” (2).

    Audit Analytics tab with the timeframe selector and Refresh Analytics button
  2. Over a given timeframe, analytics presents audit results, detailing their distribution, key defects, and proportions relative to the total audits completed.

    Distribution of audit results and key defects over the selected timeframe
  3. Lastly, from the “Settings” tab, the user can configure IP address and port.

    Settings tab with IP address and port configuration
  4. If the “NOK Images Preview” switch button is enabled, NOK images will be visible in the Audit History page as below.

    NOK image previews shown on the Audit History page once the switch is enabled
Watch the video: Audit Analytics

Systems integration

Shop-floor integration

Each ReliAudit is triggered externally by a data acquisition API, which acts as the systems integration interface:

DataAcq.API

ReliAudit can communicate with custom DataAcq.APIs tailored to specific shop-floor needs and systems integration requirements, provided they comply with ReliAudit's communication standards.

Hardware

Hardware blueprints

ReliAudit runs on Relimetrics Machine Inspection Equipment (RMIE). Four hardware blueprints cover the range of audit scenarios on the shop floor — pick the one that matches how many viewpoints the inspection needs and how the part presents itself to the cameras.

Single Camera

A single static camera inspection system suitable for audits from a single viewpoint.

Static MVS

A static multi-camera inspection station system suitable for audits that require multiple viewpoints.

Robotic MVS

A robotic gantry with mounted multi-camera setup for audits that require multiple and variable viewpoints.

Scanning MVS

A line-scanning setup suitable for high-resolution inspection of flat surfaces.

Relimetrics also offers ready-to-use data acquisition APIs that comply with each of these blueprints, so an RMIE can be integrated without writing the trigger interface from scratch.

Seeing it run

The blueprints in action

Two of the blueprints on real hardware — a multi-camera station and a line-scanning setup.

ReliMVS in action
ReliScanner in action

The edge module

What ReliAudit does

ReliAudit is the edge module of ReliVision for deploying and monitoring the AI solutions built and trained in ReliTrainer. It communicates with ReliTrainer over secure VPN connections to receive ready-to-deploy pipelines and solution updates, and to send audit results and statistics back. Its web interface lets users review results and give feedback from any browser, right on the shop floor.

1

Runs your solutions

Executes AI solutions built and deployed by ReliTrainer, when triggered by the data acquisition API.

2

Generates audit results

Executes configurable logic across one or several AI solutions involved in a single audit instance.

3

Stores them locally

Saves audit results to a local database, to be exported if and when needed.

4

Presents and collects feedback

Presents results through a web interface and accepts Accept / Dispute decisions on them, to improve performance and adapt to changing conditions.

This is some text inside of a div block.

Multiple ReliAudit modules can be connected to a single ReliTrainer.