﻿ Gas emissions reduction using machine learning

# Gas emissions reduction

Gas emissions reduction is one of the key issues industrial companies have to adress nowadays, both because of an ethical necessity and because of the new legal frameworks regulating pollution levels. It is often difficult to detect how to reduce this emissions appealing to trial and error. A machine learning model can help locating what actions to put in motion in order to reduce the atmospheric pollution produced by an instalation.

This approach promises cost savings because it makes possible to know how changes in factories' control variables will affect gas emissions beforehand.

Contents:

## Objectives

Gas emissions reduction tries to model atmospheric pollution so it is possible to see how its dependency of the control variables works.

The challenge is to get information on variables that can be easily controlled without decreasing the factories' profit.

## Benefits

It allows to perform the optimum changes in the factories' control variables in order to reduce gas emissions.

## Approach

The way to gas emissions reduction is to create an approximation model that takes in some input variables related to out target and estimates the latter.

Neural networks can model the correct values of the target variable so we can know its dependency.

That allows to save costs and time on decission making as to how to reduce a factory's emissions.

## Data set

The data set contains measurements from our system or process.

It comprises state, control, and performance variables.

State variables are those inputs that determine the system's performance and are not actionable by the company's technicians.

Some examples of state variables are:

• The ambient temperature in a combined cycle power plant.
• The humidity in a turbine room.

Control variables are those inputs that determine the performance of the system and can be set by the company's technicians.

Two examples of control variables are:

• The power production in a power plant.
• The combustion airflow in a furnace.

Performance variables are the outputs of the system and depend on the state and the control variables.

## Mathematical model

The model of a process is a mathematical description that adequately predicts the physical system's response to all anticipated inputs.

More specifically, it relates the performance variables with the state variables and the control variables.

$$performance\_variables = function(state\_variables, control\_variables)$$

Neural networks are algorithms used to fit multi-dimensional and non-linear functions from data sets.

The inputs to the neural network include the state and control variables. The outputs from the neural network are the predicted performance variables of the system for that scenario.

## Response optimization

The objective of the response optimization algorithm is to exploit the mathematical model to look for optimal operating conditions.

Indeed, the predictive model allows us to simulate different operating scenarios and adjust the control variables to improve efficiency.

More specifically, performance optimization can be formulated as follows:

For a given set of states, determine the controls that minimize or maximize the performance variables.

The next figure illustrates the response optimization process.

As we can see, for a given state value, s, the control value, c*, minimizes the gas emissions.

## Conclusions

Gas emissions reduction makes companies save money and time since meassure taking becomes a software issue, which can improve planning and decission making.

Neural Designer uses machine learning to build predictive models that represent a broad range of variables associated with gas emissions reduction.