Artificial Intelligence Assisted Dynamic Control of Environmental Emissions From Hybrid Energy Process Plants (HEPP)

U Tuzun

doi:10.3389/fenrg.2020.00179

Abstract

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. 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 multi-layer environmental perceptron (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.

Highlights

Industrial process emissions of greenhouse gases, VOCs and particulates are shown to represent some 20–30% of all environmental emissions in industrialized economies
Reducing greenhouse gas emissions and improving air quality are two interrelated challenges for world economies in combatting climate change and degradation of natural habitats; refer to Erickson and Brase (2019). 7th Environment Action Programme (7th EAP) mandated by EU aims to develop by 2018 “strategy for nontoxic environment that is conducive to innovation and the development of sustainable substitutes including non-chemical solutions”; refer to European Environment Agency [EEA] (2016) National Emissions Ceilings Directive (2016/2284/EU) and the Clean Air Programme
It is appropriate to consider the potential use of the multi-layer environmental perceptron (MLEP) with industrial plants engaged in (i) synthetic chemicals/materials production, (ii) bio-chemicals/biomaterials extraction from natural and agricultural products, and (iii) gas and liquid fuels production

Summary

INTRODUCTION

Industrial process emissions of greenhouse gases, VOCs and particulates are shown to represent some 20–30% of all environmental emissions in industrialized economies (see for example, Erickson and Brase, 2019). The operational data training (as seen in Figure 3B) using the digital platform is affected by the development of 4 task algorithms: (i) estimation of variability of material flow rates, (ii) estimation of variability of emissions of different kinds, (iii) estimation of operational disruption rates and (iv) re-current anomaly detection and Environmental Neural Switch when spatial variability takes precedence over temporal variability and vice versa Issues such as noise elimination, inputoutput signal time drift, and cumulative time-series pattern recognition indexed to sample reference states are computed to build up a reference library of the “known states” of the process plant operation. The additional challenge is imposed by the difficulty of smart guessing as to the likely duration of the “harmful state” and the optimal path to recovery to the “preferred state.” To be able to perform these additional functions effectively, the MLEP needs to have capability for “evaluative decision-making” which requires the higher level of cognitive recognition and assessment typically observed with human brain activity subjected to a situate metacognitive learning environment (see for example Tuzun, 2020a)

DISCUSSION

CONCLUSION

DATA AVAILABILITY STATEMENT