Environmental pollution management is about the sustainable development effects of enterprises and the quality of life of people. However, the frequent occurrence of various types of enterprises polluting the environment in recent years has revealed many problems, such as the lack of monitoring by relevant central agencies, the ineffective supervision by local governments, and the failure of public complaints. This paper considers the rent-seeking phenomenon of enterprises in pollution prevention and control, constructs a tripartite evolutionary game model between enterprises, local governments and central government, analyzes the evolutionary stability of each participant’s strategy choice, explores the relationship between the influence of each factor on the strategy choice of the three parties, and further analyzes the stability of the equilibrium point in the tripartite game system. The results show that there is no evolutionary equilibrium strategy in the current Chinese environmental governance system; the reward and punishment policies of the local government and central government have a guiding effect on the strategy choices of enterprises in a short period of time, but the guiding effect will gradually weaken after a period of time, and cannot completely curb the irregular strategies of enterprises; the dynamic reward scheme can effectively alleviate the fluctuation of the game system and make the strategy choices of enterprises converge to the ideal state.

Identifying abnormal process operation with spatial-temporal data remains an important and challenging work in many practical situations. Although spatial-temporal data identification has been extensively studied in some domains, such as public health, geological condition, and environment pollution, the challenge associated with designing accurate and convenient recognition schemes is very rarely addressed in modern manufacturing processes. This paper proposes a general recognition framework for identifying abnormal process with spatial-temporal data by employing a convolutional neural network (CNN) model. Firstly, motivated by the pasting case study, the spatial-temporal data are transformed into process images for capturing spatial and temporal interrelationship. Then, the CNN recognition model is presented for identifying different types of these process images, leading to the identification of abnormal process with spatial-temporal data. The specific architecture parameters of CNN are determined step by step. According to the performance comparison with alternative methods, the proposed method is able to accurately identify the abnormal process with spatial-temporal data.

No abstract