Multiple Linear Regression Model Based on Neural Network and Its Application in the MBR Simulation

and Applied Analysis 3 Table 1: Data table of the collected fluxes, pressure, and so forth. Time Temperature Pressure MLSS of inflow MLSS of outflow Total resistance Fluxes h ◦C MPa mg/L mg/L ×1012m−1 L/m2h 1 24 0.016 343.38 70.48 0.185 46.4 2 24 0.0168 378.15 83.87 0.2403 45.5 3 24 0.0175 392.42 87.06 0.2989 45.3 4 24 0.0243 472.43 85.63 0.3796 42.2 5 24 0.0268 483.73 59.62 0.3957 45.1 6 24 0.0291 583.16 95.05 0.441 42.2 7 24 0.0325 556.43 85.46 0.5119 39.7 8 24 0.0362 503.56 71.91 0.6075 37.3 9 24 0.0351 591.41 105.46 0.7143 31.4 10 24 0.0385 561.85 107.63 0.8421 28.9 11 24 0.0269 612.42 107.95 0.7623 21.7 12 24 0.0226 655.47 81.61 0.9737 14.5 13 24 0.0198 712.43 103.98 1.1659 11.2 14 24 0.0193 615.12 91.01 1.2911 10.5 15 24 0.0187 715.89 95.52 1.254 9.4 It can be seen from the data of Table 1, and after 15 hours, the relationship between total resistance and membrane fluxes as showen in Figure 1. The relationship between pressure andmembrane fluxes is shown in Figure 2. The relationship betweenMLSS of inflow and membrane fluxes is shown in Figure 3. 2.3. Establishment of an MBR Mathematically Experimental Model For MBR simulation system, the establishment of an appropriate mathematically experimental model can evaluate and simulate the existing system. Through the simulation system, we can find problems in time, adjust the system’s parameters, and get a more stable and reasonable treatment effect. We can also guide the design of the new system, so that researchers can design the reactor more reasonably and scientifically. Mathematical modeling is a complex process. For the relationship between the total drag and membrane fluxes, we can see the inverse relationship in Figure 1. The resistance gradually becomes larger, while the membrane fluxes gradually become smaller, as the relationship between them is