East Netherlands
AI-based Process Control: ARMAC bv & Radboud University
-
AI based quality control: Royal Eijkelkamp BV & Radbound University
​
(Neha Awasthi @ Radboud University)
NEED for AI:
​
Need of improved process control and industrial automation software by inclusion of:
-
Machine learning and AI based process monitoring routines
-
Process analysis and weaknesses detection routines
-
Routines for Process optimization in view of sustainability
AI REGIO SOLUTION:
​
The solution will integrate machine learning and AI routines, possibly in combination with FIWARE or APACHE, in operational process control and industrial automation software, for improved process monitoring, in order to promote the added value of these machine learning and AI routines in combination with all kinds of sensors for better and more sustainable process control. Possibly in combination with LCA. Also included is model maintenance (predict how long an AI model is valid).
EXPECTED BENEFITS:
​
-
energy consumption reduction
-
more efficient use of feedstock and less waste production
-
experience with AI technology in process monitoring for the users of the test facility, as well as the owners
AI-based Process Control w/ ARMAC bv (Neha Awasthi @ Radboud University)
​
The experiment is related to the Implementation of machine learning and AI routine-based process control and process analysis software (in view of process sustainability) in operational process control and industrial automation software of ARMAC bv, in order to promote the added value of these machine learning and AI routines for the company and its clients in the region.
NEED for AI:
​
Need of improved process control and industrial automation software by inclusion of:
-
machine learning and AI based process monitoring routines
-
detect and predict faults and planning maintenance.
-
predictive maintenance for process optimization in view of sustainability
AI REGIO SOLUTION:
​
The solution will integrate machine learning and AI-routines in quality control and industrial automation software, for improved monitoring of sensors, their lifetimes and faults. This leads to better and sustainable quality control and predictive maintenance.
EXPECTED BENEFITS:
​
Develop AI-powered quality control system by linking the measurement and maintenance data. Hence, improve maintenance process and make it sustainable and efficient.
AI-Based Quality Control, w/ Royal Eijkelkamp (Neha Awasthi @ Radboud University)
​
The experiment is related to the development of a sustainable optimized quality control system. The goal is to develop an AI-powered quality control that will relate the measurement and maintenance data to deliver a grade (score) of the quality measurement, detect system faults, and detect their root cause. The system will use expert systems, multivariate data analysis, and deep learning models as the solution’s core.