Long short-term memory (LSTM)
Assembly Line
Recurrent neural networks as virtual cavity pressure and temperature sensors in high-pressure die casting
High-pressure die casting (HPDC) is a permanent mold-based production technology that facilitates the casting of near net shape components from nonferrous alloys. The pressure and temperature conditions within the cavity impact the cast product quality during and after the conclusion of the die filling process. Die surface cavity sensors can deliver information describing the conditions at the die-casting interface. They are associated with high costs and limited service lifetimes below the achievable total cycle count of the die inserts and therefore ill-suited for industrial use cases. In this work, the suitability of long short-term memory (LSTM) recurrent neural networks (RNN) for substituting physical cavity temperature and pressure sensors virtually after the production ramp-up or at the end of the sensor service life is investigated. Training LSTMs with data of 233 casting cycles with different process parameters provides networks which are then applied to 99 further cycles. The prediction accuracy is investigated for different time interval lengths in the solidification and cooling phase. For longer time intervals, the cavity pressure prediction deteriorates, potentially due to a highly individual and hardly ascertainable buildup of casting distortion and internal stresses. Overall, however, the accuracy of the developed LSTMs is excellent for the cavity temperatures and good for the cavity pressures.
Time series prediction model using LSTM-Transformer neural network for mine water inflow
Mine flooding accidents have occurred frequently in recent years, and the predicting of mine water inflow is one of the most crucial flood warning indicators. Further, the mine water inflow is characterized by non-linearity and instability, making it difficult to predict. Accordingly, we propose a time series prediction model based on the fusion of the Transformer algorithm, which relies on self-attention, and the LSTM algorithm, which captures long-term dependencies. In this paper, Baotailong mine water inflow in Heilongjiang Province is used as sample data, and the sample data is divided into different ratios of the training set and test set in order to obtain optimal prediction results. In this study, we demonstrate that the LSTM-Transformer model exhibits the highest training accuracy when the ratio is 7:3. To improve the efficiency of search, the combination of random search and Bayesian optimization is used to determine the network model parameters and regularization parameters. Finally, in order to verify the accuracy of the LSTM-Transformer model, the LSTM-Transformer model is compared with LSTM, CNN, Transformer and CNN–LSTM models. The results prove that LSTM-Transformer has the highest prediction accuracy, and all the indicators of its model are well improved.
Long–short-term memory encoder–decoder with regularized hidden dynamics for fault detection in industrial processes
The ability of recurrent neural networks (RNN) to model nonlinear dynamics of high dimensional process data has enabled data-driven RNN-based fault detection algorithms. Previous studies have focused on detecting faults by identifying the discrepancies in data distribution between the faulty and normal data, as reflected in prediction errors generated by RNN models. However, in industrial processes, variations in data distribution can also result from changes in normal control setpoints and compensatory control adjustments in response to disturbances, making it hard to differentiate between normal and faulty conditions. This paper proposes a fault detection method utilizing a long short-term memory (LSTM) encoder–decoder structure with regularized hidden dynamics and reversible instance normalization (RevIN) to compactly represent high-dimensional measurements for effective monitoring. During training, the hidden states of the model are regularized to form a low-dimensional latent space representation of the original multivariate time series data. As a result, the prediction errors of the latent states can be used to monitor the abnormal dynamic variations, while the reconstruction errors of the measured variables are used to monitor the abnormal static variations. Furthermore, the proposed indices can reflect operating conditions, even when the distribution of test data changes, which helps distinguish faults from normal adjustments and disturbances that controllers can settle. Data from numerical simulation and the Tennessee Eastman process are used to illustrate the effectiveness of the proposed fault detection method.