Deep-Learning-Based Power Generation Forecasting of Thermal Energy Conversion.

Yu-Sin Lu,Kai-Yuan Lai

doi:10.3390/e22101161

Abstract

ORC is a heat to power solution to convert low-grade thermal energy into electricity with relative low cost and adequate efficiency. The working of ORC relies on the liquid–vapor phase changes of certain organic fluid under different temperature and pressure. ORC is a well-established technology utilized in industry to recover industrial waste heat to electricity. However, the frequently varied temperature, pressure, and flow may raise difficulty to maintain a steady power generation from ORC. It is important to develop an effective prediction methodology for power generation in a stable grid system. This study proposes a methodology based on deep learning neural network to the predict power generation from ORC by 12 h in advance. The deep learning neural network is derived from long short-term memory network (LSTM), a type of recurrent neural network (RNN). A case study was conducted through analysis of ORC data from steel company. Different time series methodology including ARIMA and MLP were compared with LSTM in this study and shows the error rate decreased by 24% from LSTM. The proposed methodology can be used to effectively optimize the system warning threshold configuration for the early detection of abnormalities in power generators and a novel approach for early diagnosis in conventional industries.

Highlights

To validate the prediction performance of the multivariate long short-term memory network (LSTM) model for 1 h and 12 h, five models are employed for comparison: the Univariate LSTM model, the multivariate LSTM model, the Univariate Multiplayer perceptron (MLP) model, the multivariate MLP model and the Autoregressive integrated moving average (ARIMA) model
The forecasting results based on the Univariate LSTM, multivariate LSTM, univariate MLP, multivariate MLP, and ARIMA models are shown in Figures 14 and 15
Estimating the amount of power generated from thermal energy conversion is crucial for the effective operation of power systems

Summary

Introduction

In today’s society, more than 90% of energy is generated as thermal energy, most of which is emitted into the environment as waste heat after use. When waste heat is discharged into lakes and rivers, the water temperature will rise sharply, causing the death of animals and plants It may increase the heat in the atmosphere and affect global climate change. Recycling schemes for low-temperature waste heat are highly conducive to energy conservation and carbon emission reduction Such schemes help governments reduce the load on electrical grids. Organic rankine cycle (ORC) products are advantageous for their use of mature technology as well as high reliability and low costs. Such products are considered the most economical solution to low-temperature thermal energy conversion with the highest conversion efficiency [2]

Methods

Results

Conclusion