Complex industrial processes usually contain hybrid characteristics; that is, static and dynamic characteristics (SADC) exist between process variables, which bring great challenges to operating performance assessment. However, the existing achievements rarely consider the hybrid correlations. Although dynamic principal component analysis has explored this issue, it treats the static and dynamic variables indiscriminately, which artificially increases the dimension of modeling data to a certain extent. In view of the above problem, this paper proposes a distributed modeling scheme based on hybrid characteristics decomposition. First, an effective process decomposition algorithm that takes into account SADC is presented. Second, the suitable modeling strategy for each subblock is selected according to the strength of the SADC. Subsequently, the assessment results of different subblocks are merged through Bayesian inference, so that the final decision of triggering nonoptimal alarm is simplified. The proposed distributed principle component analysis-canonical variate analysis (D-PCA-CVA) algorithm more adequately mines the information contained in process data, thereby improving the ability of detecting nonoptimal status. Finally, the superior performance of D-PCA-CVA in operating performance assessment is verified through numerical example and gold hydrometallurgy process.

A key biodiversity area (KBA) is one of the important emerging area-based conservation measures that is being implemented recently in China; however, the human pressure faced by a KBA is still unclear. This study analyzed the spatiotemporal variation of human pressure on KBAs from 1990 to 2017 and compared it with the human pressure on national natural reserves (NNRs) through a case study of the Qinghai–Tibet Plateau. In addition, changes in the trend of human pressure before and after 2010 were analyzed to examine the influence of conservation policies on human pressure. Results showed that human pressure on KBAs and NNRs gradually increased from 1990 to 2017. Furthermore, the growth rates and mean values of human pressure in KBAs were higher than those in NNRs. After the implementation of conservation policies in 2010, the growth rates of human pressure on both KBAs and NNRs have significantly slowed, and the areas with negative growth in both KBAs and NNRs have gradually expanded. In addition to providing an understanding of the changing spatiotemporal trends of human pressure on KBAs, this study can serve as a reference to formulate policies for the improvement of the effectiveness of conservation.

Industrial process data often contains missing values due to network transmission errors and sensor failures, etc. Unlike some fields such as biology and climatic science, missing values imputation (MVI) for online data is necessary for industrial processes, because most of the data-based intelligent decision support systems demand a complete training data set and online samples. To the best of the authors' knowledge to date, limited results on MVI for both a training data set and online samples are reported. How to achieve a comprehensive and highprecision MVI scheme in line with industrial reality is still an open problem. Directed toward the complicated correlations among variables of plant-wide industrial process (PWIP), we first propose an improved feature subset selection algorithm based on the time shift correlation and a newly defined selection criterion. Second, for each variable with missing values, the feature subset with strong correlations to this variable is selected. In this way, the time-lagged correlations both within and across variables are made full use of. Through applying variational Bayesian principal component analysis (VBPCA) into the resulting feature subsets, a novel distributed shift correlation-based VBPCA (DSCVBPCA) technique is developed to achieve a better imputation effect. Thereafter, the moving window strategy and the modified DSCVBPCA with tactfully set parameters are integrated to accomplish the MVI for online samples. Finally, the experiments much closer to the actual situations of PWIP are conducted on a numerical example and gold hydrometallurgy, indicating that the proposed imputation scheme can be a promising alternative for the MVI of industrial processes.