Rule Mining and Intelligent Prediction in Process Plant Design

Process plant design involves a variety of engineering backgrounds and specialized knowledge. With abundant latent design rules not being extracted, the existing modeling methods present the disadvantages of low efficiency and deficient model quality. In that sense, a Frequent-Type-Tree model for mining process plant design rules is proposed. The model constructs a Frequent Type Tree by analyzing component attributes and topological correlations in plant models and provides real-time intelligent predictions by querying the tree for future design. Experimental results show that the proposed model can mine valuable latent modeling knowledge in various application backgrounds. The mined knowledge is then used to shrink ranges of component selection by a large margin while future modeling efficiency and design quality is improved significantly.