Toward Distributed Data Processing on Intelligent Leak-Points Prediction in Petrochemical Industries

Focusing on the leak-points in petrochemical industries, this paper discusses the key factors (i.e., equipment temperature, gas pressure, and diffusion rate) in petrochemical industries. Data from sensors of petrochemical industries need to be timely operated because of time sensitivity and it is hard to achieve associated information from sensors located in production sites. To this end, we propose a three-level framework based on improved back propagation (TLBP). The real-time data streams are processed according to the arriving time in input layer. At the same time, a neuron-optimizing solution is introduced in learning process to deal with redundant and invalid neurons, thereby accelerating the response speed of learning and reducing the prediction time. Finally, we propose an improved mechanism of the multidimensional learning factor to lower the learning error and higher convergence rate. Meanwhile, to fulfill the distributed prediction on leak-points, we see one three-level data-processing unit as a logic machine with multiple operators. Using the assignment scheduling, the general scheduling problem is split into the common subproblem of every operator and the system overhead is reduced. With the processed data we can obtain the relative location or diffusion radius of leak-points, as well as the area of leak-points. Simulation results show that the TLBP performs better than related algorithms in different metrics. Besides, the adaptability of TLBP is verified in leak-points prediction of petrochemical equipment from the processed data.