Hierarchical Self-Attention Network for Industrial Data Series Modeling With Different Sampling Rates Between the Input and Output Sequences.

For industrial processes, it is significant to carry out the dynamic modeling of data series for quality prediction. However, there are often different sampling rates between the input and output sequences. For the most traditional data series models, they have to carefully select the labeled sample sequence to build the dynamic prediction model, while the massive unlabeled input sequences between labeled samples are directly discarded. Moreover, the interactions of the variables and samples are usually not fully considered for quality prediction at each labeled step. To handle these problems, a hierarchical self-attention network (HSAN) is designed for adaptive dynamic modeling. In HSAN, a dynamic data augmentation is first designed for each labeled step to include the unlabeled input sequences. Then, a self-attention layer of variable level is proposed to learn the variable interactions and short-interval temporal dependencies. After that, a self-attention layer of sample level is further developed to model the long-interval temporal dependencies. Finally, a long short-term memory network (LSTM) network is constructed to model the new sequence that contains abundant interactions for quality prediction. The experiment on an industrial hydrocracking process shows the effectiveness of HSAN.

Quality Prediction Modeling for Industrial Processes Using Multiscale Attention-Based Convolutional Neural Network.

Soft sensors have been increasingly applied for quality prediction in complex industrial processes, which often have different scales of topology and highly coupled spatiotemporal features. However, the existing soft sensing models usually face difficulties in extracting the multiscale local spatiotemporal features in multicoupled complex process data and harnessing them to their full potential to improve the prediction performance. Therefore, a multiscale attention-based CNN (MSACNN) is proposed in this article to alleviate such problems. In MSACNN, convolutional kernels of different sizes are first designed in parallel in the convolutional layers, which can generate feature maps containing local spatiotemporal features at different scales. Meanwhile, a channel-wise attention mechanism is designed on the feature maps in parallel to get their attention weights, representing the significance of the local spatiotemporal feature at different scales. The superiority of the proposed MSACNN over the other state-of-the-art methods is validated through the performance evaluation in two real industrial processes.

Siglec9 + tumor-associated macrophages predict prognosis and therapeutic vulnerability in patients with colon cancer.

BACKGROUND: Siglec9 has been identified as an immune checkpoint molecule on tumor-associated macrophages (TAMs). Nevertheless, the expression profile and clinical significance of Siglec9 + TAMs in colon cancer (CC) are still not fully understood. METHODS: Two clinical cohorts from distinct medical centers were retrospectively enrolled. Immunohistochemistry and immunofluorescence were conducted to evaluate the infiltration of immune cells. Single-cell RNA sequencing and flow cytometry were utilized to identify the impact of Siglec9 + TAMs on the tumor immune environment, which was subsequently validated through bioinformatics analysis of the TCGA database. Prognosis and the benefit of adjuvant chemotherapy (ACT) were also evaluated using Cox regression analysis and the Kaplan-Meier method. RESULTS: High infiltration of Siglec9 + TAMs was associated with worse prognosis and better benefit from 6-month ACT. Siglec9 + TAMs contributed to immunoevasion by promoting the infiltration of immunosuppressive cells and the dysfunction process of CD8 + T cells. Additionally, high infiltration of Siglec9 + TAMs was associated with the mesenchymal-featured subtype and overexpression of the VEGF signaling pathway, which was validated by the strongest communication between Siglec9 + TAMs and vascular endothelial cells. CONCLUSIONS: Siglec9 + TAMs may serve as a biomarker for prognosis and response to ACT in CC. Furthermore, the immunoevasive contexture and angiogenesis stimulated by Siglec9 + TAMs suggest potential treatment combinations for CC patients.

Robust Representation Learning for Power System Short-Term Voltage Stability Assessment Under Diverse Data Loss Conditions.

With the help of neural network-based representation learning, significant progress has been recently made in data-driven online dynamic stability assessment (DSA) of complex electric power systems. However, without sufficient attention to diverse data loss conditions in practice, the existing data-driven DSA solutions' performance could be largely degraded due to practical defective input data. To address this problem, this work develops a robust representation learning approach to enhance DSA performance against multiple input data loss conditions in practice. Specifically, focusing on the short-term voltage stability (SVS) issue, an ensemble representation learning scheme (ERLS) is carefully designed to achieve data loss-tolerant online SVS assessment: 1) based on an efficient data masking technique, various missing data conditions are handled and augmented in a unified manner for lossy learning dataset preparation; 2) the emerging spatial-temporal graph convolutional network (STGCN) is leveraged to derive multiple diversified base learners with strong capability in SVS feature learning and representation; and 3) with massive SVS scenarios deeply grouped into a number of clusters, these STGCN-enabled base learners are distinctly assembled for each cluster via multilinear regression (MLR) to realize ensemble SVS assessment. Such a divide-and-conquer ensemble strategy results in highly robust SVS assessment performance when faced with various severe data loss conditions. Numerical tests on the benchmark Nordic test system illustrate the efficacy of the proposed approach.

Efficiency Maximization of a Direct Internal Reforming Solid Oxide Fuel Cell in a Two-Layer Self-Optimizing Control Structure.

Control system configuration is essential for the efficiency performance of a solid oxide fuel cell (SOFC). In this paper, we aim to report a novel two-layer self-optimizing control (SOC) system for the efficiency maximization of a direct internal reforming SOFC, where the efficiency index is defined as the profit of generated electricity penalized by carbon (CO2) emission. Based on the lumped-parameter model of the SOFC, comprehensive evaluations are carried out to identify the optimal controlled variables (CVs), the control of which at constant set-points can optimize the efficiency, in spite of operating condition changes. In the lower SOC layer, we configure single variables as the CVs. The results show that the stack temperature is the active constraint which should be controlled to maintain the cell performance. In addition, the outlet hydrogen composition is identified as the optimal CV. This result differs from several previous proposals, such as methane composition. In the presence of operating condition changes, the set-point of hydrogen composition is further automatically adjusted by the upper SOC layer, where a linear combination of the SOFC measurements is configured as the CV, giving negligible efficiency losses. The cascaded two-layer SOC structure is able to maximize the SOFC efficiency and reduce carbon emission without using online optimization techniques; meanwhile, it allows for smooth and safe operations. The validity of the new scheme is verified through both static and dynamic evaluations.

Enhanced control structure design for an industrial off-gas system: Simple reconfigurations benefit the economy.

For control structure design of the industrial off-gas benchmark system, application of the Skogestad's state-of-art design procedure has suggested the scrubber inlet pressure (P si in the roaster) and one of the fan speeds (N fan1 or N_fan2 in the furnace) as the self-optimizing controlled variables CVs. In this study, we stress and advocate the gSOC-plus-BAB approach as an enhanced design toolkit for the classical and systematical design procedure. The gSOC (global self-optimizing control) is able to efficiently solve measurement combinations as CVs with improved economic performances, while the BAB (branch and bound) algorithm serves to fast screen promising measurement subsets for large-scale problems. Using the enhanced design for the off-gas system, our new findings are to control the combination of roaster's ID fan outlet pressures, 0.494P IDfan1+0.506P IDfan2 (setpoint: -257.04 Pa), and the furnace's fan pressure difference, P IDfan1- P IDfan2 (setpoint: 0). Such simple reconfigurations can dramatically reduce the average economic loss by 53.3% for the roaster and even achieve perfect optimal control for the furnace. Both steady state and dynamic evaluations are carried out to validate the reconfigured control structures. © 2017 Elsevier Inc. All rights reserved.

High Expression of CUL9 Is Prognostic and Predictive for Adjuvant Chemotherapy in High-Risk Stage II and Stage III Colon Cancer.

We evaluated the clinical implications of CUL9 expression on the prognosis and the predictive value for adjuvant chemotherapy in colon cancer. A total of 1078 consecutive patients treated with radical resection from 2008 to 2012 were included. Formalin-fixed, paraffin-embedded specimens were used as immunohistochemistry (IHC) for CUL9. For all patients, high expression of CUL9 was identified as an independent prognostic factor for overall survival (HR = 1.613, 95% CI 1.305−1.993, p < 0.001) and disease-free survival (HR = 1.570, 95% CI 1.159−2.128, p = 0.004). The prognostic value of high CUL9 expression was confirmed in an independent validation cohort from the GEO database. The efficacy of adjuvant chemotherapy was analyzed among patients with high-risk stage II and stage III disease. Those with high CUL9 expression from the full dose group had better disease-free survival (HR = 0.477, 95% CI 0.276−0.825, p = 0.006) than those from the reduced dose group. The interaction test between CUL9 expression and the treatment reached significance and was not confounded by T stage, N stage and histopathological grade. In general, high expression of CUL9 was an independent prognostic factor in patients with colon cancer. In those with high-risk stage II and stage III disease, high expression of CUL9 was associated with the benefit from standard 6-months adjuvant chemotherapy regimens.

Nonlinear Dynamic Soft Sensor Development with a Supervised Hybrid CNN-LSTM Network for Industrial Processes.

A soft sensor is a key component when a real-time measurement is unavailable for industrial processes. Recently, soft sensor models based on deep-learning techniques have been successfully applied to complex industrial processes with nonlinear and dynamic characteristics. However, the conventional deep-learning-based methods cannot guarantee that the quality-relevant features are included in the hidden states when the modeling samples are limited. To address this issue, a supervised hybrid network based on a dynamic convolutional neural network (CNN) and a long short-term memory (LSTM) network is designed by constructing multilayer dynamic CNN-LSTM with improved structures. In each time instant, data augmentation is implemented by dynamic expansion of the original samples. Moreover, multiple supervised hidden units are trained by adding quality variables as part of the layer input to acquire a better quality-related feature learning performance. The effectiveness of the proposed soft senor development is validated through two industrial applications, including a penicillin fermentation process and a debutanizer column.

New insights into the fractionation of effluent organic matter on diagnosis of key composition affecting advanced phosphate removal by Zr-based nanocomposite.

The influence of effluent organic matter (EfOM) on phosphate removal by adsorption plays an important role in evaluating the applicability of adsorbents. Currently, molecular understanding of EfOM regarding its impact on adsorption is insufficient due to a lack of appropriate EfOM fractionation/characterization protocols, as associated with the specific structure-function property of adsorbents. In this work, a combined method coupling DEAE/XAD fractionation with molecular characterization was proposed, targeting the versatile structure-function characters of nanocomposite, to reveal the composition of EfOM as well as its impact on phosphate removal by nanocomposite during long-term adsorption/regeneration runs. Zirconium-based polystyrene anion exchanger (HZO-201) was selected as a representative nanocomposite, featuring with porous networking matrix, positively charged surface and multiple adsorptive sites. The EfOM samples from three biologically treated sewage effluent sources were separated into fractions of negatively charged organic acid (OA) and hydrophobic-, transphilic-, hydrophilic-neutral/base (HPO-n/b, TPI-n/b and HPI-n/b). The combined method enables effective differentiation of the charge, aromaticity, molecular weight and functionalities of the fractions, matching the multiple structural/surface characteristics of HZO-201 and favoring the evaluation on the impact of the EfOM fractions. The interference sequence of the EfOM fractions on phosphate removal followed an order of OA > HPO-n/b > TPI-n/b > HPI-n/b. The OA fraction, characterized by negatively charged, aromatic functionalities and broad molecular weight distribution (1-5 kDa and 14 kDa), was recognized as the key interfering fraction, presumably due to its multiple adsorption pathways (i.e., ion exchange, π-π interactions and pore filling). Particularly, the low-molecular-weight OA moieties (1-4 kDa) progressively accumulated onto the nanocomposite via irreversible adsorption, causing a continuous phosphate-capacity loss by 32.70% over multiple cycles. We believe the combined fractionation/characterization method may be extended to other complex water systems to identify key influential organic matters in polishing treatment of various pollutants by adsorption.