Parameter sensitivity analysis method in nitrogen and phosphorus removal process of sewage treatment plant

• Main Authors: QIU ZHUYI, LIU YIQI, YE HONGTAO, YU GUANGPING, HUANG ZHIPENG
• Format: Patent
• Language: Chinese; English
• Published: 16.08.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a parameter sensitivity analysis method in a nitrogen and phosphorus removal process of a sewage treatment plant. The method comprises the following steps: establishing a prediction model of a sewage treatment system; defining an input space, and determining a parameter variation range according to input data; designing a frequency set, selecting a frequency set W according to the input parameter dimension, and calculating a sample capacity N; carrying out data sampling, and generating input samples obeying uniform distribution through a search curve; and parameter sensitivity analysis: calculating an r-order moment output by the system, deducing an estimated value of a variance output by the system, decomposing the real function f (s) into a Fourier series form, and further calculating an estimated value of the variance output by the parameter xi to obtain a first-order sensitivity index of the parameter xi. According to the method, FAST sensitivity analysis and a machine learning met