Technology

Integration of AI technologies into industrial domain

One of the most important challenges for developing innovative solutions in the process industry is the complexity, instability and unpredictability of their processes and impact into their value chain.

These solutions are usually running in harsh conditions, with dynamic changing in the values of process parameters, missing a consistent or at all monitoring/measurement of some parameters important for analysing process behaviour and difficult to measure in real time and sometimes, only available through quality control laboratory analysis that are responsible to get the traceability of origin and quality of feedstocks, materials and products.

 
 

s-X-AIPI technologies

An innovative AI data pipeline with autonomic computing capabilities (self-X AI and autonomic manager)

  • AI applications continually updated (self-X abilities) by integrating data with reduced human intervention.

  •  Autonomic Manager supporting Human in the loop roles


Novel architecture and realistic datasets

Datasets and their respective algorithms will be derived from the demonstration in four realistic use cases of process industry.

self-X AI

self-X AI is the combination of the AI as the intelligent processing system along with an Autonomic manager (proposed by IBM)

The autonomic manager is based on MAPE-K model (continuous Monitoring-Analyzing-Planning-Execution flow based on the Knowledge of the AI system under control) for developing self-improving AI systems.

The project’s application and demonstration aims to widen the adoption of such smart systems, which can facilitate many complex tasks and ensure the optimal operation of the AI applications at a low cost.

The new AI applications will be, to some extent, self-Managed to improve their own performance incrementally. This will be realized by an adaptation loop, which enables “learning by doing” using MAPE-K model and self-X abilities as proposed by autonomic computing. The improvement process should be based on continuous self- Optimization ability.

Moreover, in the case of having some problems in the functioning of an AI component, the autonomic manager should activate self-Configuration, self-Healing and self-Protection abilities as needed, based on Knowledge from AI system.

 

Autonomic Computing abilities

Self-Configuration

for easier integration of new systems for change adaptation

Self-Optimization

automatic resource control for optimal functioning

Self-Healing

detection, diagnose and repair for error correction

Self-Protection

identification and protection from attacks in a proactive manner