This paper presents a novel neural network (NN) to control an ammonia refrigerant evaporator. Inspired by the latest findings on the biological neuron, a dynamic synaptic unit (DSU) is proposed to enhance the information processing capacity of artificial neurons. Treating the dynamic synaptic activity after the nonlinear somatic activity helps to capture the dynamics demarcated by the Gaussian activation pertaining to the input space. This practice leads to a remarkable reduction in curse of dimensionality. The proposed NN architecture has been compared with two other conventional architectures; one with dynamic neural units (DNUs) and the other with nonlinear static functions as perceptrons. The objective is to control evaporator heat flow rate and secondary fluid outlet temperature while keeping the degree of refrigerant superheat in the range 4–7 K at the evaporator outlet by manipulating refrigerant and evaporator secondary fluid flow rates. The drawbacks of conventional approaches to this problem are discussed, and how the novel method can overcome them are presented. An evolutionary approach is adopted to optimize the parameters of the NN controllers. Then evaporator process model is accomplished as a combination of governing equations and a sub NN resulting in a simple and sufficiently accurate model. The effectiveness of the proposed dynamic NN controller for the evaporator system model is validated using experimental data from the ammonia refrigeration plant. 相似文献
In this paper, a new solution cycle in the double absorption heat transformer is presented and the thermodynamic performance of this new cycle is simulated based on the thermodynamic properties of aqueous solution of lithium bromide. The results show that this new cycle is superior to the cycle being studied by some researchers. This new solution cycle has a wider range of operation in which the system maintains the high value of COP and has larger temperature lifts and operation stability. The relationship between the absorber and the absorbing evaporator is more independent and this makes the operation and control of the system more easier. 相似文献
“Grey-box” modelling combines the use of first-principle based “white-box” models and empirical “black-box” models, offering particular benefits when: (a) there is a lack of fundamental theory to describe the system or process modelled; (b) there is a scarcity of suitable experimental data for validation or (c) there is a need to decrease the complexity of the model. The grey-box approach has been used, for example, to create mathematical models to predict the shelf life of chilled products or the thermal behaviour of imperfectly mixed fluids, or to create models that combine artificial neural networks and dynamic differential equations for control-related applications. This paper discusses the main characteristics of white-box, black-box and their integration into grey-box models, the requirements and sourcing of accurate data for model development and important validation concepts and measures. 相似文献
A theoretical and experimental study has been carried out for a residential brine-to-water CO2 heat pump system for combined space heating and hot water heating. A 6.5 kW prototype heat pump unit was constructed and extensively tested in order to document the performance and to study component and system behaviour over a wide range of operating conditions. The CO2 heat pump was equipped with a unique counter-flow tripartite gas cooler for preheating of domestic hot water (DHW), low-temperature space heating and reheating of DHW.
The CO2 heat pump was tested in three different modes: space heating only, DHW heating only and simultaneous space heating and DHW heating. The heat pump unit gave off heat to a floor heating system at supply/return temperatures of 33/28, 35/30 or 40/35 °C, and the set-point temperature for the DHW was 60, 70 or 80 °C. Most tests were carried out at an evaporation temperature of −5 °C, and the average city water temperature was 6.5 °C. The experimental results proved that a brine-to-water CO2 heat pump system may achieve the same or higher seasonal performance factor (SPF) than the most energy efficient state-of-the-art brine-to-water heat pump systems as long as: (1) the heating demand for hot water production constitutes at least 25% of the total annual heating demand of the residence, (2) the return temperature in the space heating system is about 30 °C or lower, (3) the city water temperature is about 10 °C or lower and (4) the exergy losses in the DHW tank are small. 相似文献