Traditional monitoring algorithms use the normal data for modeling, which are universal for different types of faults. However, these algorithms may perform poorly sometimes because of the lack of fault information. In order to further increase the fault detection rate while preserving the universality of the algorithm, a novel dynamic weight principal component analysis (DWPCA) algorithm and a hierarchical monitoring strategy are proposed. In the first layer, the dynamic PCA is used for fault detection and diagnosis, if no fault is detected, the following DWPCA based second layer monitoring will be triggered. In the second layer, the principal components (PCs) are weighted according to its ability in distinguishing between the normal and fault conditions, then the PCs which own larger weight are selected to construct the monitoring model. Compared to the DPCA method, the proposed DWPCA algorithm establishes the monitoring model by combining the information of fault. Afterwards, the DWPCA based variable relative contribution and a novel control limit for the variable relative contribution are presented for the fault diagnosis. Finally, the superiority of the proposed method is demonstrated by a numerical case and the Tennessee Eastman (TE) process.

Plant-wide processes often have the characteristics of large-scale and multiple operating units. Moreover, due to the closed-loop control, it is possible that the fault never affects product quality. In this article, a novel data-driven method called multisubspace orthogonal canonical correlation analysis (CCA) is proposed, which can not only tell whether the fault occurs but can also judge whether the fault affects the product quality in real time. First, to reduce process analysis complexity and to construct an accurate monitoring model, the original process variable space is divided into four subspaces. Second, the developed orthogonal CCA is conducted on process data and quality data for correlation feature extraction. Then, the quality-related and quality-unrelated features are obtained. Afterward, a total of six monitoring statistics are constructed and integrated to four statistics with physical interpretation via the Bayesian fusion strategy. Finally, the developed method is tested under an industrial case.

As industrial technology develops, industrial processes become increasingly large and complex, the traditional methods are difficult to extract features that can represent the condition of the whole process and the effect of fault on quality indicators. Therefore, a novel multiblock decouple convolutional neural network (multiblock DCN) algorithm is proposed. First, key process variables are selected, and process variables are grouped into multiple blocks for the following monitoring. Then, in each block, the proposed DCN constructs a regression model between key process variables and quality indicators, in which the regression model utilizes an improved convolutional neural network as a feature extractor and a decoupling layer as a feature regularizer. Afterward, the monitoring results of each block are integrated into a global monitoring index based on Bayesian theory. After fault detection, variable oblivion contribution plot is presented to locate faulty variables. Finally, two industrial cases are used to demonstrate the effectiveness of multiblock DCN.

In this paper, a novel multimode quality related process monitoring method called multi-subspace elastic network (MSEN) is proposed. To make mode partition more precisely, this paper develops a novel clustering algorithm based on the neighborhood information and subtractive clustering algorithm. In each single mode, unlike conventional process monitoring models which only focus on whether the fault occurs, a novel elastic network (EN) based quality related process monitoring model is established to judge whether the fault is quality related or not. In addition, to select the most suitable monitoring model for online data, the k nearest neighbor rule and the voting strategy are applied. Once the fault is detected, the contribution plot method is conducted in both quality related and unrelated subspace for fault diagnosis. At last, the proposed MSEN method is tested under the continuous stirred tank reactor (CSTR) to verify its superiority and advantage.

Radiation therapy is a fundamental cancer treatment in the clinic. However, to satisfy the clinical requirements, radiologists have to iteratively adjust the radiotherapy plan based on experience, causing it extremely subjective and time-consuming to obtain a clinically acceptable plan. To this end, we introduce a transformer-embedded multi-task dose prediction (TransMTDP) network to automatically predict the dose distribution in radiotherapy. Specifically, to achieve more stable and accurate dose predictions, three highly correlated tasks are included in our TransMTDP network, i.e. a main dose prediction task to provide each pixel with a fine-grained dose value, an auxiliary isodose lines prediction task to produce coarse-grained dose ranges, and an auxiliary gradient prediction task to learn subtle gradient information such as radiation patterns and edges in the dose maps. The three correlated tasks are integrated through a shared encoder, following the multi-task learning strategy. To strengthen the connection of the output layers for different tasks, we further use two additional constraints, i.e. isodose consistency loss and gradient consistency loss, to reinforce the match between the dose distribution features generated by the auxiliary tasks and the main task. Additionally, considering many organs in the human body are symmetrical and the dose maps present abundant global features, we embed the transformer into our framework to capture the long-range dependencies of the dose maps. Evaluated on an in-house rectum cancer dataset and a public head and neck cancer dataset, our method gains superior performance compared with the state-of-the-art ones. Code is available at https://github.com/luuuwen/TransMTDP.