Anaerobic digestion is associated with various crucial variables, such as biogas yield, chemical oxygen demand, and volatile fatty acid concentration. Real-time monitoring of these variables can not only reflect the process of anaerobic digestion directly but also accelerate the efficiency of resource conversion and improve the stability of the reaction process. However, the current real-time monitoring equipment on the market cannot be widely used in the industrial production process due to its defects such as expensive equipment, low accuracy, and lagging analysis. Therefore, it is essential to conduct soft sensor modeling for unmeasurable variables and use auxiliary variables to realize real-time monitoring, optimization, and control of the an-aerobic digestion process. In this paper, the basic principle and process flow of anaerobic digestion are first briefly introduced. Subsequently, the development history of the traditional soft sensor is systematically reviewed, the latest development of soft sensors was detailed, and the obstacles of the soft sensor in the industrial production process are discussed. Finally, the future development trend of deep learning in soft sensors is deeply discussed, and future research directions are provided.

Remaining useful life (RUL) prediction is critical for ensuring the safety, reliability, and efficient operation of complex industrial systems. Conventional deep neural networks, such as long short-term memory network and convolutional neural network mainly adopt local recurrent and pooling operations, which have notable limitations in global modeling in RUL prediction for complex industrial systems. Although the emergence of graph neural network (GNN)-based approaches can solve the above-mentioned problems, there are few reports on using GNN for RUL prediction under cross-domain conditions. Consequently, a novel transferable topology-aware graph pooling network is proposed for RUL prediction under cross-domain conditions. Specifically, this article integrates local and global voting to construct a topology-aware graph pooling network. Furthermore, a loss function is constructed to describe domain differences, so that the RUL prediction under cross-domain conditions is accomplished. Considering most of the existing deep learning approaches are closed-box models, this article designs an in-depth interpretability analysis based on the feature distribution and integrated gradient for the proposed approach. The effectiveness of TTAPGN is demonstrated by a commercial aircraft turbofan engine dataset, and a bearing degradation dataset from Xi'an Jiaotong University.

Anaerobic digestion technology is an effective way to solve the problem of urban kitchen waste. Volatile fatty acid (VFA) is an essential intermediate product in the anaerobic digestion process. Real-time monitoring of the concentration of VFA can not only directly reflect the anaerobic digestion process and improve resource conversion efficiency but also effectively avoid the reactor operation failure caused by acidification. Traditional soft sensors of VFA cannot adapt to the dynamic characteristics of industrial process. In this paper, a dynamic soft sensor based on spatiotemporal graph convolution network is developed. The spatial and temporal information of the anaerobic digestion process is extracted through graph convolutional network (GCN) and gated recurrent unit (GRU) respectively. With the purpose of further improving the prediction accuracy and generalization ability of the model, the adaptive adjacency matrix and graph attention mechanism are introduced into the model to solve the over-smoothing problem of GCN, and the semi-supervised learning mechanism based on manifold regularization is introduced to fully mine data information of unlabeled samples. Then, the gated unit is used to realize the information fusion of different dimensional features and the selection of model depth. At last, a dynamic soft sensor based on the semi-supervised gated spatiotemporal graph attention network is established to estimate the concentration of VFA in real time. Compared with baseline models such as GCN and GRU, the root mean square error of this model is reduced by 17.34% and 15.54%, respectively.