Time_series_forecast_with_LSTM_network

This repository contains the implementation of a recurrent neural network (LSTM from keras library) with the purpose of forecasting target time series, given the targets historical records and covariates. The project uses a toy data set, while focusing on the data transformation tasks (pandas dataframes to 3D numpy arrays required by recurrent networks) and on the hyperparameters tuning tasks, taking advantage of keras_tuner package.

Optimize_pipe_diameter_and_pressure_drop

The code in this project solves the problem of finding the optimal diameter for a straight pipe conveying an incompressible fluid, for user defined mass flow rates. The best design solution is considered the one that minimizes both the pressure drop per unitary pipe length and the pipe diameter. Solutions are ranked according to TOPSIS method. The user can input the pipe absolute roughness, to identify the pipe material, and the density and dynamic viscosity, depending from the fluid to be studied.