A deep learning approach to predict and optimise energy in fish processing industries.

The fish processing sector is experiencing increased pressure to reduce its energy consumption and carbon footprint as a response to (a) an increasingly stringent energy regulatory landscape, (b) rising fuel prices, and (c) the incentives to improve social and environmental performance. In this paper, a standalone forecasting computational platform is developed to optimise energy usage and reduce energy costs. This short-term forecasting model is achieved using an artificial neural network (ANN) to predict power and temperature at thirty-minute intervals in two cold rooms of a fish processing plant. The proposed ANN function is optimised by genetic algorithms (GA) with simulated annealing algorithms (SA) to model the relationships between future temperature and power and the system variables affecting them. To assess the accuracy of the proposed method, extensive experiments were conducted using real-world data sets. The results of the experiments indicate that the proposed ANN model performs with higher accuracy than (a) the long short-term memory (LSTM) as an artificial recurrent neural network (RNN) architecture, (b) peephole-LSTM, and (c) the gated recurrent unit (GRU). This paper finds that using GA & SA algorithms; ANN parameters can be optimised. The RMSE obtained by the ANN compared with the second-ranked method GRU was consequently 16% and 4% less for the predicted temperature and power. The results in one particular site demonstrate energy cost savings in the range of 15%–18% after applying the forecast-optimiser approach. The proposed prediction model is used in a fish processing plant for energy management and is scalable to other sites. [Display omitted] • A standalone forecasting computational platform is developed to optimise energy use. • The neural network is improved by genetic algorithms and simulated annealing. • The prediction model is used in a fish processing plant for energy management. • The model feeds into an optimiser which directs an energy management system. • The energy cost savings were 15%–18% after applying the forecast-optimiser approach. [ABSTRACT FROM AUTHOR]