| Summary: | A model digital data processing platform is proposed based on “deep-learning” methodology that can be used to identify the emissions patterns from process plants with hybrid energy recovery and energy generation facilities. The non-invasive dynamic monitoring and correlation of particulate, VOCs and other greenhouse gas emissions from semi-batch and continuous process plants is demonstrated with use of neural encoding and pattern recognition using a multi-layer perceptron and multi-stack encoder configuration. A multi-layer environmental perceptron (MLEP) is developed based on the above analyses that aims to detect patterns of emission types, rates and concentrations as a function of variation of plant operational conditions and process variables. Four different task algorithms are constructed and are currently trained for use in (i) In-Plant Product Quality Control Domain and (ii) In-Plant Process Efficiency Target Control Domain. As a further consequence, environmental impact assessment is considered within the hazards and process safety frameworks that conventionally issue sanctions and penalize non-compliance with imposition of environmental levy scales rather than offering process improvement incentives. The latter is demonstrated to be possible by facilitating dynamic corrective action and hazard prevention using MLEP platforms should emission ceilings be frequently and/or periodically exceeded in 24/7 continuous plant operations. Potential applications of the MLEP (MLEP) are illustrated in the context of dynamic emissions control and abatement in hybrid energy process plants (HEPP) and combined power plants using process-integrated CO2 capture and storage schemes.
|
|---|
