Near-infrared (NIR) spectroscopy plays a critical role in online analysis of difficult-to-measure properties of petrochemicals. In industrial applications, a calibration model among NIR spectra and properties must be established. However, it is a challenge to obtain a precision NIR model in the majority of petrochemical processes since industrial data present strong non-Gaussian and uncertainty characteristics. To deal with these problems, in the present work a probabilistic regression modeling method based on a biased minimax probability machine (BMPM) is proposed, without assuming any specific distributions for the data. In addition, a multiple locally weighted updating approach with a new supervised similarity distance is introduced to cope with process changes. The greatest advantage of the proposed approach is that it has superior capability in dealing with uncertainties and variations. The effectiveness of the method is illustrated through its application in an actual gasoline blending process and a simulated fermentation process.
Combustion optimization is an effective way to improve the efficiency of thermal power generation and reduce carbon and NOx emissions. Real-time and precise NOx emission prediction is the basis for combustion optimization control of thermal power plants. To construct an accurate NOx concentration prediction model, a novel just-in-time learning (JITL) method based on random forest (RF) is proposed in the present work. With this method, first, an improved permutation importance algorithm is proposed to extract important variables. In addition, a similarity index that incorporates temporal and spatial measures is defined to select a local training set representative of the process data. Moreover, considering the influence of model parameters on prediction performance under different working conditions, a process monitoring method based on a moving window (MW) is used to monitor the change in working conditions and guide online updating. The experimental results show that the proposed method has excellent prediction accuracy, with a coefficient of determination of 0.9319, a root-mean-square error of 3.6960 mg/m3, and an average absolute error of 2.7718 mg/m3 on the test set, making it superior to other traditional methods.
20 July 2022 in IEEE Transactions on Automation Science and Engineering
Effective fault diagnosis can be obtained by using multiblock global orthogonal projections to latent structures (MBGOPLS), but there exist certain limitations in this method in terms of block division intelligence and model robustness to outliers. Although these issues can be addressed by developing correlation analysis, such as mutual information and copula-correlation, the complex coupling relationship between variables has not been fully examined. In this study, a robust MBGOPLS is proposed to intelligently diagnose faults using a relatively stable model. First, a double hierarchical clustering method is established, in which internal hierarchical clustering is performed based on Euclidean distance to discretize the samples. Subsequently, external hierarchical clustering is adopted based on mutual information distance to divide variables into different blocks, which results in intelligent block division while suppressing the influence of outliers. Second, a robust block regression coefficient matrix (BRCM) is obtained by employing joint $\ell _{2,1}$ -norm minimization on the BRCM and prediction error of the correlation between the block input and output. Furthermore, BRCM is integrated into the MBGOPLS framework. Therefore, the proposed method is robust to outliers while retaining the diagnostic properties of MBGOPLS. Finally, the proposed method is applied in a numerical case and an actual thermal power plant. The results verify the method’s applicability and superiority. Note to Practitioners—With increasing large-scale, complex and intelligent to achieve anticipant performance, thermal power plant is prone to faults that can lead to unplanned outages. Meanwhile, complex operation mechanism and environment, and diverse data acquisition sensors make the coupling relationship between variables complex, and collected data often contain numerous outliers, which happens frequently in modern industrial process. Therefore, fault diagnosis is critical to modern industrial process, and the diagnosis accuracy and robustness are the main challenges. This forces us to ensure the block division accuracy and model robustness when using multiblock-based fault diagnosis technology. This paper proposes a robust MBGOPLS to intelligently diagnose faults of thermal power plant using a relatively stable model. Additionally, the proposed method can be extended to fault diagnosis for other large-scale processes.
1 March 2021 in Flow Measurement and Instrumentation