No abstract

No abstract

No abstract

This study proposes a novel method for detection of aflatoxin B1 (AFB1) in peanuts using olfactory visualization technique. First, 12 kinds of chemical dyes were selected to prepare a colorimetric sensor to assemble olfactory visualization system, which was used to collect the odor characteristic information of peanut samples. Then, genetic algorithm (GA) with back propagation neural network (BPNN) as the regressor was used to optimize the color component of the preprocessed sensor feature image. Support vector regression (SVR) quantitative analysis model was constructed by using the optimized combination of characteristic color components to achieve determination of the AFB1 in peanuts. In this process, the optimization performance of grid search (GS) algorithm and sparrow search algorithm (SSA) on SVR parameter was compared. Compared with GS-SVR model, the model performance of SSA-SVR was better. The results showed that the SSA-SVR model with the combination of seven characteristic color components obtained the best prediction effect. Its correlation coefficients of prediction (RP) reached 0.91. The root mean square error of prediction (RMSEP) was 5.7 μg·kg−1, and ratio performance deviation (RPD) value was 2.4. The results indicate that it is reliable to use the colorimetric sensor array with strong specificity for the determination of the AFB1 in peanuts. In addition, it is necessary to properly optimize the parameters of the prediction model, which can obviously improve the generalization performance of the multivariable model.

The sensor diagnosis system of the blast furnace axial fan is very important to the safety of the blast furnace fan control system. In view of the fact that the sensor fault detection of the blast furnace fan is not considered in the existing research, this paper proposes to use SVR to establish a fault detection model for the blast furnace fan outlet pressure sensor, and then use the improved chaotic sparrow algorithm to optimize the selection of the SVR penalty parameters and kernel function parameters Find the optimal parameters. By comparing the model prediction value and the residual error of the diagnostic sensor output value, the sensor fault diagnosis is realized. When the fault is judged, the model prediction value is used instead of the fault sensor output value to be used by the blast furnace fan control system to realize the fault-tolerant control of the blast furnace fan control system. The simulation results show that this method realizes the fault detection of the pressure sensor of the blast furnace fan and improves the safety of the blast furnace production.