─Batch process quality prediction is an important application in manufacturing and chemical industries. The complexity of batch processes is characterized by multiphase, nonlinearity, dynamics and uneven durations so that modeling of these batch processes is rather difficult. Moreover, there are other challenges in face of quality prediction. Specifically, the process trajectories over the whole running duration potentially make specific contributions to the final targets so that the prediction issue embraces tremendously high-dimensional inputs but very low-dimensional outputs. This means that the prediction suffers from a severe dimensional imbalance between inputs and outputs. Motivated by these difficulties, this paper proposes a new deep learning-based framework for complex feature representative and quality prediction. Long short-term memory is used to extract comprehensive quality-relevant hidden features from a long-time sequence in each phase, significantly reducing the predictor dimensions. And these features from different phases are further integrated and compressed by a stacked auto-encoder. A practical industrial example testifies to the efficacy of the proposed framework.

No abstract

No abstract

The development of power dispatch services to ensure power supply has put forward new requirements for the digitalization, intelligence and servitization of the dispatching system. Based on the data of power dispatch and control, the characteristics of power dispatch services to ensure power supply, and research on intelligent technology of dispatching and control to ensure power supply based on multivariate information, by establishing the data model of power supply services, and applying forms of expression such as knowledge graph, with deep neural network and rule learning technology, this paper explores and develops an intelligent robot of dispatching and control to ensure power supply based on multivariate information, which realizes the functions of interface integration of various service platforms, visualized monitoring of power supply information, and release and submission of power supply information, etc. By building intelligent applications according to the requirements of power dispatch services to ensure power supply, it effectively improves the risk prevention and control level and emergency response capacity of power system to ensure power supply, and comprehensively upgrades the safe and stable operation of power system to ensure power supply.

Research on reliability of relaying protection in smart substation not only has a positive effect on the rational configuration scheme of relaying protection in smart substation, but also can promote the stability and safety of the overall operation of power system. There are many reliability strategies for relaying protection in smart substation. In practice, the key points of relaying protection should be clarified. Based on the reality, the protection configuration should be strengthened; the voltage limited delay should be used for protection, and the protection configuration scheme of actual lines should be paid attention to, so as to improve the reliability of relaying protection in smart substation and promote the realization of stable and sustainable development of power system and smart substation.