Image

aRTi-D™ , Indicative case studies

Predictive Maintenance

tablet_1.png

A Greek hydroelectric power company was looking for a solution to monitor the operations of the generator of its Hydroelectric unit, through various sensors, with the aim of predictive maintenance and forecasting of energy production. The monitoring process included functions of collecting, evaluating, processing, storing, and monitoring the various functionally critical generator measurements.

  • A significant amount of critical information is not being used.
  • Existing equipment does not have the ability to collect and process large volumes of data.
  • Ability to monitor and control only on-site.
  • Emergency maintenance, occurs often and is very costly.

Through aRTi-D®, the health of the generator is monitored remotely and data is collected to predict and warn of expected failures as well as for the remaining lifetime. Also, through Artificial Intelligence and Machine Learning algorithms, water flow is measured and energy production is predicted with continuous and self-correcting prediction in case of change in weather data.

Result: 28% Reduction of Maintenance Costs

Production Analytics

A Greek plastic manufacturing company was looking for a solution to deal with lost production times, through the analysis of production data. Micro-outages at various points on the production line (repeated and non-repeated) trigger alarms, which cause delays in the production process, with difficulty in determining the exact cause of the problem and a serious impact on the production volume.

  • Inability to process large volumes of data from multiple sources and with high measurement accuracy, resulting in non-utilization and exploitation of real-time data.
  • Once an event occurs, there are delays in data analysis, finding the real cause and recovery.

The aRTi-D™ solution provides in a simple and automated way a holistic view of the interactions between the processes and the product flow to present the real production status. aRTi-D™ provides:

  • Overall Equipment Performance (OEE)
  • Hourly production and forecasts
  • Cause of downtimes and suggestions for improvement
  • Loss of income
  • Production trends and suggestions for improvement
laptop_3d.png

Result: 20% increase in productivity

Production Process Automation - Automated Recipe Management

mobile_1b.png

One of the largest suppliers of peptide materials in the world, was seeking to digitize, automate and improve the operation and control of its production. The requirement included monitoring and control of temperature, humidity, pressure, dosage, mixing and controlled transport of fluids for all equipment (reactors, filters, tanks, etc.).

The limitations of the existing production system were as follows:

1.  High initial investment cost

2.  Time & cost of programming & controlling the production assets.

3. No automated reports.

4. Failure to exploit a significant amount of critical information.

5. Ability to control only from within the company. 

6. Costly & time-consuming technical support.

1. Remote Monitoring and Production Control, from multiple data sources (sensors, SCADA, ERP).

2. Creation, processing & execution of automated recipes by specifying parameters and phases. Immediate configuration and adjustment of equipment operation with parameter changes.

3. Security and role-based electronic signatures  

4. Traceability of all actions (Audit trail) and reporting.

5. Recipe versioning control.

6. Technical support and remote intervention.

Result: 15% Faster Production

▶ FIND US

Alexandroupolis

Andrianoupoleos 27,

68131, Alexandroupolis, GR

info@seems.gr - +30 2551023116

Thessaloniki

Platonos 42, 55236,

Panorama - Thessaloniki, GR

info@seems.gr - +30 2317 009 269

▶ SEEMS

SEEMS is a hi-tech company which is focused on IoT solutions development employing Artificial Intelligence techniques.

SEEMS is built on a team of inspired and hardworking innovation explorers developing progressive technological solutions to improve the daily quality of life.

© 2017 | SEEMS