Search

This article considers the parameter estimation problems for the controlled autoregressive systems interfered by moving average noises. A recursive extended gradient algorithm with penalty term is proposed by using the penalty criterion function. By introducing three fictitious output variables, the original system can be decomposed into three subsystems based on the hierarchical principle. The hierarchical recursive extended gradient algorithm with penalty term is then proposed to achieve the parameter estimation. Finally, the experimental results demonstrate the effectiveness of the proposed algorithms. [ABSTRACT FROM AUTHOR]

Background Methods Results Conclusion Taxanes are the basic components of breast cancer chemotherapy. Nanoparticle albumin‐bound paclitaxel (nab‐paclitaxel) shows improved antitumor effects because of more targeted delivery. However, the effects of nab‐paclitaxel have not been systematically studied in patients with metastatic breast cancer (MBC) pretreated with taxanes. Considering the limited treatment options for MBC, this study retrospectively evaluated the clinical efficacy and adverse effects of nab‐paclitaxel in patients with taxane‐pretreated MBC.Patients who had previously received taxanes and subsequently received nab‐paclitaxel chemotherapy for MBC at Jiangsu Cancer Hospital between October 2014 and April 2022 were included for analysis. The primary end point was progression‐free survival (PFS), and the secondary end points were the objective response rate (ORR), disease control rate (DCR), clinical benefit rate (CBR), and side effects.A total of 236 female patients with MBC were included. The median PFS was 7.20 months (95% confidence interval [CI], 6.63–7.80 months), and the ORR, DCR, and CBR were 29.55% (95% CI, 23.50%–35.60%), 83.64% (95% CI, 78.70%–88.60%), and 56.36% (95% CI, 49.80%–63.00%), respectively. Following nab‐paclitaxel treatment, the median PFS of patients who were sensitive to taxanes during previous treatments was significantly longer than that of patients who were resistant to taxanes (7.57 months vs. 4.43 months, p < .001). The most common adverse events were sensory neuropathy (89.83%), neutropenia (48.73%), leukopenia (46.61%), and anemia (35.59%).Nab‐paclitaxel demonstrated clinical activity in taxane‐pretreated patients with MBC. This beneficial effect was observed both in patients who were sensitive and resistant to taxanes during previous treatments. These results suggest nab‐paclitaxel as the preferred chemotherapy regimen in patients with MBC, regardless of their sensitivity to taxanes during previous treatments. [ABSTRACT FROM AUTHOR]

This article investigates the identification issue of the bilinear system in the presence of the impulsive noise. The bilinear system based on the observer canonical form is translated into a regressive form, and a bilinear state observer is established to estimate the state variables. To overcome the effects of the impulsive noise to parameter estimation, the proposed algorithms employ a generalized continuous mixed p$$ p $$‐norm cost function, which can generate an adjustable gain that control the proportions of the error norms without resorting to a priori knowledge of the noise. Moreover, a sliding window is designed to update the dynamical data by removing the oldest data and adding the newest measurement data. An numerical example exhibits that the proposed algorithms can reduce the impact of the impulsive noise to parameter estimation and improve the parameter estimation accuracy compared with the conventional algorithms. [ABSTRACT FROM AUTHOR]

For multiphase batch process, the characteristics of process data under various batches differ. Consequently, the soft sensor model built for a particular working condition is inapplicable to other working conditions. Besides, each batch can be divided into several phases whose characteristics are probably different. To address the above problems, a soft sensor model based on phase division and transfer learning strategy is proposed. First, transfer learning strategy is adopted to construct a soft sensor model applicable to various working conditions. Specifically, geodesic flow kernel based on linear local tangent space alignment (LLTSA-GFK) algorithm is designed. By projecting process data to the common manifold subspace, the distribution difference of data between various batches is reduced and the performance of the soft sensor model is enhanced. In addition, sequence-based fuzzy clustering and just-in-time learning (JITL) are adopted to solve the multistage characteristic for batch process. The root-mean-square error (RMSE), coefficient of determination ( R 2 ) , and mean absolute error (MAE) are adopted to compare the conventional soft sensing approach (i.e., partial least-square regression based on JITL, support vector regression, and back propagation neural network) with the proposed approach. The superiority of the proposed model is verified by a fed-batch penicillin fermentation process. [ABSTRACT FROM AUTHOR]

Dynamic responses, measurement noise, and time delays in industrial processes can affect the accuracy of soft sensing models. Our goal is to create a dynamic soft sensor modeling method that is robust to the abovementioned problems. Aiming at time sequence data, a feature extraction-based model is constructed by combining convolution filtering techniques with a backpropagation neural network. In addition, training strategies based on gradient descent are proposed to ensure the efficiency and accuracy of the training process. Convolution parameters are trained with model parameters synchronously without prior knowledge. The performance is verified through simulations and industrial experiments in terms of measurement noise, sensor drifting, and dynamic modeling problems. [ABSTRACT FROM AUTHOR]

Summary: This article studies the parameter identification problem for bilinear state space models with time‐varying time delays. Considering the correlation of time delays, the Markov chain switching mechanism is adopted to model the delay sequence. Based on the observer canonical form, the bilinear state space model is transformed into a regressive form. A bilinear state observer is designed to estimate the state variables. Under the variational Bayesian scheme, the system parameters, discrete delays, and the Markov transition probabilities are identified by using the measurement data. A numerical example and a continuous stirred tank reactor simulation are employed to validate the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Olkiluoto, an island on the south-west coast of Finland, will host a deep geological repository for the storage of spent nuclear fuel. Microbially induced corrosion from the generation of sulphide is therefore a concern as it could potentially compromise the longevity of the copper waste canisters. Groundwater at Olkiluoto is geochemically stratified with depth and elevated concentrations of sulphide are observed when sulphate-rich and methane-rich groundwaters mix. Particularly high sulphide is observed in methane-rich groundwater from a fracture at 530.6 mbsl, where mixing with sulphate-rich groundwater occurred as the result of an open drill hole connecting two different fractures at different depths. To determine the electron donors fuelling sulphidogenesis, we combined geochemical, isotopic, metagenomic and metaproteomic analyses. This revealed a low diversity microbial community fuelled by hydrogen and organic carbon. Sulphur and carbon isotopes of sulphate and dissolved inorganic carbon, respectively, confirmed that sulphate reduction was ongoing and that CO2 came from the degradation of organic matter. The results demonstrate the impact of introducing sulphate to a methane-rich groundwater with limited electron acceptors and provide insight into extant metabolisms in the terrestrial subsurface. [ABSTRACT FROM AUTHOR]

The joint parameter and time-delay estimation problems for a class of nonlinear multirate time-delay system with uncertain output delays are addressed in this paper. The practical process typically has time-delay properties and the process data are often multirate, sampled with output data inevitably corrupted by uncertain delays. The linear parameter varying (LPV) finite impulse response (FIR) multirate time-delay model is initially built to describe the considered system. The problems of over-parameterization and the existence of both continuous model parameters and discrete time-delays have made the conventional maximum likelihood difficult to solve the considered problems. In order to handle these problems, the joint parameter and time-delay estimation for the LPV FIR multirate time-delay model are formulated in the expectation-maximization scheme, and the algorithm to estimate the model parameters and time-delays is derived, simultaneously based on multirate process data. The efficacy of the proposed method is verified through a numerical simulation and a practical chemical plant. [ABSTRACT FROM AUTHOR]

This paper studies the problem of parameter estimation for frequency response signals. For a linear system, the frequency response is a sine signal with the same frequency as the input sine signal. When a multi-frequency sine signal is applied to a system, the system response also is a multi-frequency sine signal. The signal modeling for multi-frequency sine signals is very difficult due to the highly nonlinear relations between the characteristic parameters and the model output. In order to obtain the parameter estimates of the multi-frequency sine signal, the signal modeling methods based on statistical identification are proposed by means of the dynamical window discrete measured data. By constructing a criterion function with respect to the model parameters to be estimated, a hierarchical multi-innovation stochastic gradient estimation method is derived through parameter decomposition. Moreover, the forgetting factor and the convergence factor are introduced to improve the performance of the algorithm. The simulation results show the effectiveness of the proposed methods. [ABSTRACT FROM AUTHOR]

The parameter estimation problem for multi‐input multi‐output Hammerstein systems is considered. For the Hammerstein model to be identified, its dynamic time‐invariant subsystem is described by a controlled autoregressive model with a communication delay. The modified Kalman filter (MKF) algorithm is derived to estimate the unknown intermediate variables in the system and the MKF‐based recursive least squares (LS) algorithm is presented to estimate all the unknown parameters. Furthermore, the hierarchical identification is adopted to decompose the system into two fictitious subsystems: one containing the unknown parameters in the non‐linear block and the other containing the unknown parameters in the linear subsystem. Then an MKF‐based hierarchical LS algorithm is derived. The convergence analysis shows the performance of the presented algorithms. The numerical simulation results indicate that the proposed algorithms are effective. [ABSTRACT FROM AUTHOR]

Apart from strong nonlinearity and time-varying behaviors in industrial processes, the hidden time-delay information, which is unfortunately overlooked in most existing modeling methods, should also be taken into account in soft sensor modeling. In view of this, a novel soft sensor, referred to as local time-delay reconstruction based moving window time difference Gaussian process regression (LTR-MWTDGPR), is proposed in this paper. To deal with the time-delay, a fuzzy curve analysis based local time-delay parameter extraction procedure is performed along with a strategy of a moving window, which simultaneously captures the process time-varying feature. Then the local window training dataset and new query sample are reconstructed according to the time-delay parameter set at the next sampling instant. Afterwards, the time difference Gaussian process regression is employed to handle the drifting feature of local reconstructed dataset. The effectiveness and accuracy of the proposed LTR-MWTDGPR approach in predicting quality variables are verified through a real sulfur recovery unit and an industrial debutanizer column. [ABSTRACT FROM AUTHOR]

A new approach for modeling and monitoring of the multivariate processes in presence of faulty and missing observations is introduced. It is assumed that operating modes of the process can transit to each other following a Markov chain model. Transition probabilities of the Markov chain are time varying as a function of the scheduling variable. Therefore, the transition probabilities will be able to vary adaptively according to different operating modes. In order to handle the problem of missing observations and unknown operating regimes, the expectation maximization algorithm is used to estimate the parameters. The proposed method is tested on two simulations and one industrial case studies. The industrial case study is the abnormal operating condition diagnosis in the primary separation vessel of oil-sand processes. In comparison to the conventional methods, the proposed method shows superior performance in detection of different operating conditions of the process. © 2014 American Institute of Chemical Engineers AIChE J, 61: 477-493, 2015 [ABSTRACT FROM AUTHOR]

This paper is concerned with theidentification problems of thelinear parameter varying (LPV) system with missing output in the presenceof the time-delay. A multiple-model approach is adopted. Local modelsvarying from one operating point to another are first described byfinite impulse response (FIR) models. To handle missing output andtime-delay, the expectation-maximization (EM) algorithm is utilizedto estimate the unknown parameters and the time-delay simultaneously.Output Error (OE) models are widely used in controller design. Therefore,the auxiliary model principle is employed to recover the OE modelsbased on the initially identified FIR models. The EM algorithm isthen used again to refine the unknown parameters of the OE modelswith the complete data set to obtain the final global model. Simulationexamples are presented to demonstrate the performance of the proposedmethod. [ABSTRACT FROM AUTHOR]

Accurate and real-time quality prediction to realize the optimal process control at a competitive price is an important issue in Industrial 4.0. This paper shows a successful engineering application of how smart soft sensors can be combined with machine learning technique to significantly save human resources and improve performance under complex industrial conditions. Ensemble learning based soft sensors succeed in capturing complex nonlinearities, frequent dynamic changes, as well as time-varying characteristics in industrial processes. However, local model regions under traditional ensemble modelling methods are highly dependent on labeled data samples and, hence, their prediction accuracy might get affected when labeled samples are limited. A novel active learning (AL) framework upon the ensemble Gaussian process regression (GPR) model is proposed for smart soft sensor design in order to overcome this drawback. Firstly, to iteratively select the most informative unlabeled samples for labeling with hierarchical sampling based AL strategy, to then apply Gaussian mixture model (GMM) technique to autonomously identify operation phases, to further construct local GPR models without human involvement, and finally to integrate the base predictors by applying the Bayesian fusion strategy. Comparative studies for the penicillin fermentation process demonstrate the reliability and superiority of the recommended smart soft sensing. The cost of human annotation can be dramatically reduced by at least half while the prediction performance simultaneously keeps high. [ABSTRACT FROM AUTHOR]