Temporally-Preserving Quantum LSTM With Multiscale Attention Mechanisms for Soft Sensor Applications

Soft sensor modeling is the task of using measurable variables to predict target ones, which may involve nonlinearity and temporally dynamics. Despite significant progress, there is a relative lack of research on soft sensor-oriented Quantum Long Short-Term Memory (QLSTM) design and application. As a novel quantum soft sensor approach, a temporally-preserving QLSTM (TP-QLSTM) is proposed by integrating with multiscale attention mechanisms. Specifically, a temporally-preserving-based adaptive variational quantum circuit is designed by establishing entanglement across temporal inputs to improve the temporally learning capability of QLSTM. Moreover, multiscale attention mechanisms are designed in the input and output parts of TP-QLSTM to learn nonlinearities and temporal dynamics from different feature dimensions and temporal ones, as well as from historical hidden states and temporal outputs. In addition, a referential attention-based autoregressive forecasting strategy is proposed as output module of TP-QLSTM to predict the target results. Experiments on two soft sensor cases demonstrate the effectiveness and practicality of our method. Note to Practitioners—In industrial processes, soft sensors are critical for achieving comprehensive state awareness and predictive management. However, practical soft sensors often struggle with complex nonlinear and time-dependent relationships in dynamic processes. As an innovative attempt to enhance soft sensing from a quantum algorithm perspective, we propose a TP-QLSTM by integrating multiscale attention mechanisms. Through designing adaptive quantum circuits that preserve temporal correlations and incorporating multiscale attention mechanisms, our method effectively captures multiscale dynamics and nonlinearities from process data. This enables accurate and robust predictions of key variables in industrial settings. Experiments on real cases confirm that our method achieves high prediction accuracy while maintaining low computational latency—with an average inference time of less than 0.6 ms per sample. A current limitation is that the quantum algorithm is implemented using simulated quantum circuits, which restricts the full exploitation of quantum parallelism. Future work will focus on deploying the model to hardware platforms that support real quantum circuit computation, thus enabling efficient training and inference.