Multi-index control strategy from cement calcination denitration system: a model predictive control method for combined control of nitrogen oxide and ammonia escape.

The cement industry is one of the main sources of NOx emissions, and automated denitration systems enable precise control of NOx emission concentration. With non-linearity, time delay and strong coupling data in cement production process, making it difficult to maintain stable control of the denitration system. However, excessive pursuit of denitration efficiency is often prone to large ammonia escape, causing environmental pollution. A multi-objective prediction model combining time series and a bi-directional long short-term memory network (MT-BiLSTM) is proposed to solve the data problem of the denitration system and achieve simultaneous prediction of NOx emission concentration and ammonia escape value. Based on this model, a model predictive control framework is proposed and a control strategy of denitration system with multi-index model predictive control (MI-MPC) is built based on neural networks. In addition, the differential evolution (DE) algorithm is used for rolling optimization to find the optimal solution and to obtain the best control variable parameters. The control method proposed has significant advantages over the traditional PID (proportional integral derivative) controller, with a 3.84% reduction in overshoot and a 3.04% reduction in regulation time. Experiments prove that the predictive control framework proposed in this paper has better stability and higher accuracy, with practical research significance.

Ultrasensitive fluorescence detection of gonyautoxins in seawater using a novel molecularly imprinted nanoprobe.

Gonyautoxins (GTXs), a group of potent neurotoxins belonging to paralytic shellfish toxins (PSTs), are often associated with harmful algal blooms of toxic dinoflagellates in the sea and represent serious health and ecological concerns worldwide. In the study, a highly selective and sensitive fluorescence nanoprobe was constructed based on photoinduced electron transfer recognition mechanism to rapidly detect GTXs in seawater, using specific entrapment of molecularly imprinted polymers (MIPs) combined with fluorescence analyses. The green emissive fluorescein isothiocyanate was grafted in a silicate matrix as a signal transducer and fluorescence intensity of the nanoprobe with a core-shell structure exhibited a strong enhancement due to efficient analyte blockage in a short response time. Under optimal conditions, the developed MIPs nanoprobe presented an excellent analytical performance for spiked seawater samples including a recovery from 94.44 % to 98.23 %, a linear range between 0.018 nmol L-1 and 0.36 nmol L-1, as well as good accuracy. Furthermore, the method had extremely high sensitivity, with limit of detection obtained as 0.005 nmol L-1 for GTXs and GTX2/3. Finally, the nanoprobe was applied for the determination of GTXs in seven natural seawater samples with GTXs mixture (0.035-0.058 nmol L-1) or single GTX2/3 (0.033-0.050 nmol L-1), and the results agreed well with those of a UPLC-MS/MS method. The findings of our study suggest that the constructed MIPs-based fluorescence enhancement nanoprobe was suitable for rapid, selective and ultrasensitive detection of GTXs, particular GTX2/3, in natural seawater samples.

Improving cement production process with data-augmented sequence to sequence-Wasserstein generative adversarial networks model for accurate prediction of f-CaO.

This paper proposes a method to address the issue of insufficient capture of temporal dependencies in cement production processes, which is based on a data-augmented Seq2Seq-WGAN (Sequence to Sequence-Wasserstein Generate Adversarial Network) model. Considering the existence of various temporal scales in cement production processes, we use WGAN to generate a large amount of f-CaO label data and employ Seq2Seq to solve the problem of unequal length input-output sequences. We use the unlabeled relevant variable data as the input to the encoder of the Seq2Seq-WGAN model and use the generated labels as the input to the decoder, thus fully exploring the temporal dependency relationships between input and output variables. We use the hidden vector containing the temporal characteristics of cement produced by the encoder as the initial state of the gate recurrent unit in the decoder to achieve accurate prediction of key points and continuous time. The experimental results show that the Seq2Seq-WGAN model can achieve accurate prediction of continuous time series of free calcium and offer direction for subsequent production planning. This method has high practicality and application prospects, and can provide strong support for the production scheduling of the cement industry.

Multi-objective prediction for denitration systems in cement: an approach combining process analysis and bi-directional long short-term memory network.

Selective Non-Catalytic Reduction (SNCR) can improve the denitration process and reduce NOx emissions by accurizing prediction of NOx concentration and ammonia escape. However, there are inevitable time delays and nonlinearity problems in the prediction of NOx emission. To reduce NOx concentration quickly in SNCR, excessive ammonia spraying often causes a large amount of ammonia to escape, resulting in secondary pollution. Therefore, it is particularly important to monitor ammonia escape. To solve the above problems, this paper proposes a framework by specifically analyzing the cement denitration process and combining a multi-objective time series bi-directional long short-term memory network (MT-BiLSTM). Among them, the model achieves multi-objective prediction of NOx emission concentration and ammonia escape simultaneously. In addition, time series containing delay information are introduced in the input layer to eliminate the influence of delay. Based on the bi-directional LSTM model, the dropout strategy is adopted to improve the generalization of the model and the Adam optimizer is applied to improve the network performance. Besides, through the multi-step prediction of NOx emission at 3 time points, the dynamic nature of the data is preserved, which provides dynamic information support for realizing the automation of denitration system. The prediction performance of the MT-BiLSTM model is experimentally validated, and the results demonstrate that it can reliably predict both NOx and ammonia escape. The model achieves more accurate and reliable results for the prediction of flue gas concentrations compared with other methods such as SVR, DTR and LSTM. Therefore, the MT-BiLSTM model provides a basis for achieving NOx emission reduction and accurate ammonia injection.

A spatio-temporal data decoupling convolution network model for specific surface area prediction in cement grind process.

The specific surface area is one of the important indicators for measuring the quality of cement products. Realizing accurate prediction for specific surface area is very important for the production scheduling of the cement industry, energy conservation and consumption reduction and improvement of cement performance. However, due to the non-linearity, uncertainty, multiple interference, dynamic time-varying delay and multi scales in cement grinding process, it is difficult to establish an accurate soft-sensing model for cement quality prediction. Aiming at the above problems, we proposed a spatio-temporal decoupling convolution neural network model (STG-DCNN) to predict specific surface area by extracting and fusing data features in temporal and spatial dimension. To complete the prediction of specific surface area, we established the temporal series map and spatial series map by the production variables data according to the mechanism of cement grinding process. Then, sliding window technique was utilized to match the time scale in temporal series map and construct variable coupling relationship in spatial series map. The prediction accuracy, robustness and superiority of the proposed method were demonstrated by experiments results implemented on the actual cement grinding quality management database in a cement production enterprise.

A soft sensor model based on long&short-term memory dual pathways convolutional gated recurrent unit network for predicting cement specific surface area.

The specific surface area of cement is an important index for the quality of cement products. But the time-varying delay, non-linearity and data redundancy in the process industry data make it difficult to establish an accurate online monitoring model. To solve the problems, a soft sensor model based on long&short-term memory dual pathways convolutional gated recurrent unit network (L/S-ConvGRU) is proposed for predicting the cement specific surface area. In this paper, first, as the linear coupling constraint inside the gated recurrent unit network (GRU) hinders the flow of information, parameters L and S are introduced into convolutional gated recurrent unit network (ConvGRU). L and S are decimals in the range (0, 1) which changed its internal linear constraint relationship and enhanced the feature extraction capability of the model. Then, two spatio-temporal feature extraction pathways are designed: long-term memory enhancement pathway and short-term dependence pathway, which capture long-term and short-term time-varying delay information from the sample data. Finally, the two feature extraction pathways mentioned above are applied to the L/S-ConvGRU model and the extracted spatio-temporal features are fused to achieve accurate prediction of the specific surface area of cement. The model was trained using raw data from the cement plant and the experimental results show that L/S-ConvGRU has higher precision and better generalization capability.

A Synchronous Prediction Model Based on Multi-Channel CNN with Moving Window for Coal and Electricity Consumption in Cement Calcination Process.

The precision and reliability of the synchronous prediction of multi energy consumption indicators such as electricity and coal consumption are important for the production optimization of industrial processes (e.g., in the cement industry) due to the deficiency of the coupling relationship of the two indicators while forecasting separately. However, the time lags, coupling, and uncertainties of production variables lead to the difficulty of multi-indicator synchronous prediction. In this paper, a data driven forecast approach combining moving window and multi-channel convolutional neural networks (MWMC-CNN) was proposed to predict electricity and coal consumption synchronously, in which the moving window was designed to extract the time-varying delay feature of the time series data to overcome its impact on energy consumption prediction, and the multi-channel structure was designed to reduce the impact of the redundant parameters between weakly correlated variables of energy prediction. The experimental results implemented by the actual raw data of the cement plant demonstrate that the proposed MWMC-CNN structure has a better performance than without the combination structure of the moving window multi-channel with convolutional neural network.

Prediction of nitrogen oxide emission concentration in cement production process: a method of deep belief network with clustering and time series.

The concentration of nitrogen oxide (NOx) emissions is an important environmental index in the cement production process. The purpose of predicting NOx emission concentration during cement production is to optimize the denitration process to reduce NOx emission. However, due to the problems of time delay, nonlinearity, uncertainty, and data continuity in the cement production process, it is difficult to establish an accurate NOx concentration prediction model. In order to solve the above problems, a NOx emission concentration prediction model using a deep belief network with clustering and time series features (CT-DBN) is proposed in this paper. Particularly, to improve data sparsity and enhance data characteristics, a clustering algorithm is introduced into the model to process the original data of each variable; the time series containing delay information are introduced into the input layer, which combines previous and current variable data into time series data to eliminate the influence of the time delay on the prediction of NOx emission concentration. In addition, restricted Boltzmann machine (RBM) is used to extract data features, and a gradient descent algorithm is used to reversely adjust network parameters to establish a deep belief network model (DBN). Experiments prove that the method in this paper has higher accuracy, stronger stability, and better generalization ability in predicting NOx emission concentration in cement production. The CT-DBN model realizes the accurate prediction of NOx emission concentration, provides guidance for denitration control, and reduces NOx emissions.

Online cement clinker quality monitoring: A soft sensor model based on multivariate time series analysis and CNN.

The content of free calcium oxide (f-CaO) in cement clinker is an important index for cement quality. Aiming at the characteristics of strong coupling, time-varying delay and highly non-linearity in cement clinker production, a soft sensor model based on multivariate time series analysis and convolutional neural network (MVTS-CNN) is proposed for the online f-CaO content monitoring. Based on the process industry characteristics, the MVTS-CNN modeling involves the detailed analysis of coupling relationship and time-varying delay in cement production and the application of neural network in multivariate time-series feature extraction. The main researches and contributions are fourfold: First, the strong coupling in the production system is further analyzed, and the proposed model is focused on the data coupling between specific processes, not the control coupling. Second, a multivariate time series analysis method is designed to select the time series that may have direct impacts on the f-CaO content in different production conditions, which is founded on the information on time delay range and longest active duration. Third, a multivariate time series feature extraction method is designed and adopted in the MVTS-CNN model to extract the multivariate time series features, such as active duration difference features, coupling features, nonlinear features and key time series features. Fourth, a new timing matching method, which is combined the rough timing matching of multivariate time series and the detailed timing matching of key features, is proposed to deal with the time-varying delay in various production conditions. Compared with traditional CNN, support vector machines (SVM) and long-short term memory networks (LSTM), the results demonstrate that the MVTS-CNN model has higher accuracy, better generalization ability and superior robustness.

LncRNA BX357664 inhibits cell proliferation and invasion and promotes cell apoptosis in human colorectal cancer cells.

Colorectal cancer represents a great burden for patients worldwide. Long noncoding RNA BX357664 is an RNA that was identified by microarray technique in renal cell carcinoma. The function of BX357664 in solid tumors remains largely unknown. The present study aimed to investigate the expression profile and functional role of BX357664 in human colorectal cancer progression. The transcription levels of BX357664 were initially examined in vivo and in vitro. An overexpression plasmid was constructed in order to examine the effects of BX357664 overexpression on cell proliferation, apoptosis, migration and invasion. The results demonstrated that BX357664 was significantly downregulated in clinical colorectal cancer tissues and cell lines. Overexpression of BX357664 decreased cell proliferation rates and cell colony formation capacities in HCT116 and HT-29 cells. Following BX357664 overexpression, HCT116 and HT-29 cells exhibited reduced migration and invasion capacities. Would closure was also blunted by >50% following overexpression of BX357664 in HCT-116 and HT-29 cells. In addition, the cell cycle regulators Cyclin B1, CDC25C and Cyclin D1 as well as the mesenchymal marker N-cadherin were downregulated, whereas the epithelial marker E-cadherin was upregulated by BX357664 overexpression. Finally, HCT116 and HT-29 cell apoptosis was induced and activities of caspase-3 and caspase-9 increased significantly following BX357664 overexpression. The present data suggested that BX257664 negatively regulated cell proliferation and metastasis and promoted cell apoptosis in colorectal cancer. These observations provided novel evidence that BX357664 might serve as a tumor suppressor and a potential therapeutic target in the treatment of colorectal cancer in the clinic.

Low serum calcium is associated with left ventricular systolic dysfunction in a Chinese population with coronary artery disease.

Whether serum calcium is associated with heart systolic function in patients with established coronary artery disease (CAD) and acute myocardial infarction (AMI) remains to be elucidated. This study is aimed to assess the association between serum calcium and left ventricular systolic dysfunction in a Chinese population of CAD. The cross-sectional study included 5938 CAD patients with and without AMI in China. The factors associated with AMI and left ventricular ejection fraction (LVEF) were evaluated. The data showed that AMI patients had lower serum calcium levels (2.11 ± 0.13 vs 2.20 ± 0.10 mmol/l, P < 0.001) than those without AMI. Multiple logistic regression analysis exhibited that serum calcium (OR: 0.000, 95% CI: 0.000-0.001) was one of the independent factors correlated with AMI. CAD patients with and without AMI when LVEF <50% had lower serum calcium levels than those when LVEF ≥50% respectively. Serum calcium was independently associated with LVEF and LVEF <50% in CAD patients with and without AMI respectively using multivariate analysis. The independent association between serum calcium and LVEF still existed among CAD patients when LVEF ≥50%. Serum calcium levels are significantly decreased following AMI. Low serum calcium is independently correlated with left ventricular systolic dysfunction in CAD patients with and without AMI.

Association between estimated glomerular filtration rate, ankle-brachial index, and recurrent ischemic stroke in a Chinese population of ischemic stroke patients.

BACKGROUND: Very few studies have examined combined association of estimated glomerular filtration rate (eGFR) and ankle-brachial index (ABI) on recurrent ischemic stroke in patients with ischemic stroke in Chinese populations. PATIENTS AND METHODS: A Chinese population of 1219 ischemic stroke patients was followed up in this six-year prospective study. RESULTS: 1080 ischemic stroke patients with complete follow-up data were included in the statistical analysis. A total of 245 ischemic stroke patients (22.7 %) had recurrent ischemic stroke during follow-up. The Incidence of recurrent ischemic stroke was significantly increased with decreasing eGFR levels and that of patients with eGFR < 30 ml/min/1.73m2 was the highest. Hazard ratio (HR) of eGFR < 30 ml/min/1.73m2 to recurrent ischemic stroke was 2.633 (95 % CI: 1.653 - 4.194) compared with that of eGFR ≥ 60 ml/min/1.73m2 after adjusting for other potential confounders using Cox regression analysis. Incidence of recurrent ischemic stroke was significantly increased with simultaneously decreasing eGFR and ABI. The highest percentage (71.4 %) of patients with eGFR < 30 ml/min/1.73m2 and ABI ≤ 0.4 simultaneously had recurrent ischemic stroke during follow-up. HR of eGFR < 30 ml/min/1.73m2 and ABI ≤ 0.4 simultaneously with recurrent ischemic stroke was 9.415 (95 % CI: 3.479 - 25.483) compared with that of eGFR ≥ 60 ml/min/1.73m2 and ABI > 1.0 to ≤ 1.4 respectively CONCLUSIONS: Low ABI and low eGFR together had synergistic effects on increasing recurrent ischemic stroke of ischemic stroke patients during a long-term follow-up.