Process identification with multiple neural network models

This paper describes the identification of chemical processes with multiple neural network models. This concept is called a 'multimodel' approach. The multimodel approach presents a flexible framework which allows the integration of other model paradigms. Three different methods to construct neural network multimodels are presented. First, a priori knowledge is used to decompose the input domain into operating regimes. Each regime is modelled by a different neural network. In the second multimodel approach, unsupervised learning in form of clustering and SOMs is used to split the input domain. The third approach uses a gating neural network to divide the input space. In contrast to the first two approaches, the non-linear gated network approach allows the multim odel to simultaneously learn a suitable decomposition and the mapping in each regime. All three approaches are evaluated for a fed-batch fermentation.     

Harnstoffhydrolyse für die selektive katalytische Reduktion von NOx: Vergleich der Flüssig‐ und Gasphasenzersetzung

In order to reduce the NO_x concentration in car exhausts usually the selective catalytic reduction with ammonia is used. However, to avoid the transport of ammonia in vehicles urea is applied as NH₃ precursor. Controlled urea decomposition before the injection into the exhaust gas system itself may be accomplished by the use of a separate reactor. Urea decomposition to ammonia in the liquid phase under pressure in a heated reactor was compared to its decomposition in the gas phase. In the liquid phase, higher conversion rates relative to the reactor volume were realized than in the gas phase. Catalysts which showed high activity in the gas phase influenced the decomposition in the liquid phase only slightly.     

Evaluation of Performance of Diesel Particulate Filters Through Integrated Multi-Scale Computer Calculations

Wall-flow channel models and soot deposition models based on micro scale considerations are integrated into global 3D diesel particulate filter simulations. In addition, transient and steady-state simulations are combined to understand at the same time short- and long-time behaviour of the diesel particulate filter (DPF). The functionality of the simulation tool is achieved and correlations with measured data encourage the use of the model as a tool to predict DPF behaviour.     

On the limits of expert systems and engineering models in process control

The review is based on an analysis of current literature of expert systems and of system engineering models in dynamic process control. It starts with an analysis of the mental operations and cognitive requirements needed for supervisory control. Mental models are discussed as a function of situational requirements as well as of personal strategies. Systems engineering models and expert systems are briefly described and their function as decision support tools evaluated. Criteria are the overall functionality, similarity of knowledge bases and reasoning strategies of the human and the support system, adaptability to the operator's skill level and self-explanation of the support system in the interaction mode. As a result, system engineering models are only of limited value for knowledge-based process control. Expert systems seem to be very valuable tools for augmenting human decision making in process control, if the interaction problem can be solved.     

High-Temperature Hall Measurements on BaSnO3Ceramics

Simultaneous Hall and conductivity measurements were performed in situ between 650° and 1050°C on n-type semiconducting BaSnO₃ceramics. The variation of the Hall mobility and the Hall carrier density as a function of oxygen partial pressure between 10² and 10⁵ Pa and of temperature was investigated. At temperatures below 900°C the conductivity exhibits a dependence on temperature and oxygen partial pressure which is mainly determined by variations of the Hall mobility. Above 900°C most of the significant dependence is due to a variation in carrier density. Furthermore, a simple defect model assuming doubly ionized oxygen vacancies and acceptor impurities is discussed for BaSnO₃.