Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism

Han, Yongming; Fan, Chenyu; Xu, Mengya; Geng, Zhiqiang; Zhong, Yanhua

doi:10.1016/j.applthermaleng.2019.114072

Cited by 54 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was clear that the LSTM-NN model had the highest prediction accuracy among all models. Similarly, Han et al [19] established a model in production prediction and energy saving of complex chemical processes using LSTM and the results also showed that the average relative error results of the LSTM were obviously better than the BP. In addition, MSE and RMSE which served to assess the differences between the expected and actual values showed the same result.…”

Section: Comparison Between Bp-nn and Lstm-nnmentioning

confidence: 98%

“…[18] However, the main difference between them is that BP-NN of knowledge obtained during the training phase is distributed in the whole network in the form of connection weights and thresholds between neurons, and the LSTM-NN also uses internal memory units to store knowledge. [19,29] The structure ofLSTMblockis shown in Figure 2, configured mainlybyinput gate (i), forget gate (f), output gate (o) and memory cell state. [12] Specifically, memory cell state as the crucial element runs down through the entire chain to solve the problem of gradient vanishing and explosion, which traditional recurrent neural network (RNN) encounters and stores the state information at a time.…”

Section: Predictive Modelsmentioning

confidence: 99%

“…[12] Specifically, memory cell state as the crucial element runs down through the entire chain to solve the problem of gradient vanishing and explosion, which traditional recurrent neural network (RNN) encounters and stores the state information at a time. [19] The input of the hidden layer containing the LSTM block includes the output of the input layer and the output of the hidden layer in the previous time step that is a good way to learn the long-term dependencies between data.…”

Section: Predictive Modelsmentioning

confidence: 99%

“…Yu et al [16] established and compared different predictive models (Arrhenius model, BP-NN and radial basis function neural network) for quality changes of brined bream fillets stored at 270-282 K. However, BP-NN can easily fall into local minimum and is slow in learning speed. [17] In recent years, LSTM has been widely concerned and studied, when it comes to time-series prediction, such as oil production forecasting, [18] production of complex chemical processes prediction [19] and protein structure prediction. [20] Currently, the application of LSTM-NN in the food industry is not much explored area of research, and there is no precedent about the application of LSTM-NN to predict the storage time of aquatic products.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Storage time prediction of glazed frozen squids during frozen storage at different temperatures based on neural network

Tan

Wang

et al. 2020

International Journal of Food Properties

View full text Add to dashboard Cite

In this study, quality changes in water-holding capacity, weight loss, color, texture properties, and total sulfhydrylcontent of glazed frozen squids during frozen storage at −5, −10, −20, −30 and −40°C, were determined. In addition, backpropagation neural network (BP-NN) and long short-term memory neural network (LSTM-NN) model were established to predict storage time of glazed frozen squids, and then these two models were performed with a comparative study. The results showed that the influence on the quality of the squids during frozen storage at different temperatures had significant difference (P < .05), and at the lower storage temperatures, the declined rate of squids' quality was slower, especially. However, changes in the total SH content of squid stored at −30 and −40°C, were not significant differences in the first 60 days. The squid frozen at −5°C for 80d, reached the end of the shelf life. Both BP-NN and LSTM-NN model ware reliable models for predicting the storage time of glazed frozen squid. Experimental results of the LSTM-NN model provided an improvement in the accuracy of prediction compared with those obtained by using the BP-NN model, in which the mean absolute percentage error (MAPE) was 5.01% that was lower than the results by BP-NN model (7.67%). However, the LSTM-NN model had some shortcomings in terms of training time compared with the BP-NN model. The use of LSTM-NN provides a technique to predict accurately the storage time of glazed frozen squid.

show abstract

Section: Comparison Between Bp-nn and Lstm-nnmentioning

confidence: 98%

Section: Predictive Modelsmentioning

confidence: 99%

Section: Predictive Modelsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Storage time prediction of glazed frozen squids during frozen storage at different temperatures based on neural network

Tan

Wang

et al. 2020

International Journal of Food Properties

View full text Add to dashboard Cite

show abstract

“…However, according to Wang et al [22], BP-NN has the weak multioutput ability and self-learning ability. LSTM-NN, as a new neural network model, is used in lithium battery lifetime prediction [23], complex chemical process yield prediction [24], protein structure prediction [25], but applying LSTM-NN to aquatic product shelf-life prediction is almost not reported.…”

Section: Introductionmentioning

confidence: 99%

Shelf-Life Prediction of Glazed Large Yellow Croaker (Pseudosciaena crocea) during Frozen Storage Based on Arrhenius Model and Long-Short-Term Memory Neural Networks Model

Chu

Tan

et al. 2021

Fishes

View full text Add to dashboard Cite

In this study, the changes in centrifugal loss, TVB-N, K-value, whiteness and sensory evaluation of glazed large yellow croaker were analyzed at −10, −20, −30 and −40 °C storage. The Arrhenius prediction model and long-short-term memory neural networks (LSTM-NN) prediction model were developed to predict the shelf-life of the glazed large yellow croaker. The results showed that the quality of glazed large yellow croaker gradually decreased with the extension of frozen storage time, and the decrease in quality slowed down at lower temperatures. Both the Arrhenius model and the LSTM-NN prediction model were good tools for predicting the shelf-life of glazed large yellow croaker. However, for the relative error, the prediction accuracy of LSTM-NN (with a mean value of 7.78%) was higher than that of Arrhenius model (with a mean value of 11.90%). Moreover, the LSTM-NN model had a more intelligent, convenient and fast data processing capability, so the new LSTM-NN model provided a better choice for predicting the shelf-life of glazed large yellow croaker.

show abstract

A Hybrid Machine Learning Model for Urban Mid- and Long-Term Electricity Load Forecasting

Tang

zhihui

Zhang

et al. 2023

Lecture Notes on Data Engineering and Communications Technologies

View full text Add to dashboard Cite

Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism

Cited by 54 publications

References 21 publications

Storage time prediction of glazed frozen squids during frozen storage at different temperatures based on neural network

Storage time prediction of glazed frozen squids during frozen storage at different temperatures based on neural network

Shelf-Life Prediction of Glazed Large Yellow Croaker (Pseudosciaena crocea) during Frozen Storage Based on Arrhenius Model and Long-Short-Term Memory Neural Networks Model

A Hybrid Machine Learning Model for Urban Mid- and Long-Term Electricity Load Forecasting

Contact Info

Product

Resources

About