The Quantum-difference Evolutionary Algorithm And Its Application In The Energy Utilization Optimization Of The Steam Network

The steam system is an important part of chemical devices’utility system, but widespread phenomenon about lack of testing information, energy consumption and configuration depend on experience gives, wasting energy。The polyethylene unit steam network system have complex structure, it has various kinds of steam equipments, lack of testing information, the parameters for the model is complicated and its energy consumption and configuration depend on experience given.Firstly, this paper puts forward a method about the steam piping network system’s condition identification to different energy consumption in order to understand the real-time situation of steam system’s energy consumption intuitively and quickly. This method based on affinity propagation clustering that can solve big set of data’s clustering problem quickly and effective. As it is hard to find preference parameters and damping factor, this paper by using PSO to find the most optimal parameters in order to achieve the best clustering effect。 This method is applied test both in classic data set and the steam piping network of ethylene plant’s condition identification, the results show the effectiveness of this method。Then, for steam pipe network system’s condition that has operation potential, this paper puts forward the support vector machine as the soft sensor model to provide the accurate non-linear foundation model for the optimization of the steam piping network. A steam network model from the energy consumption is constructed based on material balance, energy conservation, product quality. This model is a problem of mixed integer nonlinear programming (MINLP), it is calculated with adaptive mixed coding differential evolution(AMCDE).Finally, the optimization effect is obvious, saving an average1.94kilogram standard oil per ton ethylene.