A novel bearing current signal diagnosis method combining variational modal decomposition and improved random forests.

A new fault diagnosis approach based on bearing current signals is proposed in this paper. First, in view of strong background noise of the current signal, the variational modal decomposition method is applied to decompose the bearing current signal to obtain multiple intrinsic mode functions, and then the intrinsic mode functions are constructed as the input feature vector according to the kurtosis. Second, to avoid the influence of random forest parameters on the random forest classifier, a random forest faulty bearing diagnostic model optimized by the whale algorithm is established. Finally, the accuracy rate and confusion matrix are adopted to evaluate the prediction effects of both established and traditional models. The classification accuracy of the real damaged bearing fault type can reach 95.11%. The fault diagnosis accuracy of manually damaged bearings can reach 93.83%. The results show that the method proposed in this paper has high accuracy and good generalization ability for bearing fault diagnosis.

Rapid separation and determination of carbamate insecticides using isocratic elution pressurized capillary electrochromatography.

An isocratic elution pressurized CEC (pCEC) system was used to separate and determine ten carbamate insecticides. It was found that introduction of the electrical field, supplementary pressure, and SDS in the proposed method greatly improved the speed, column efficiency, selectivity, and repeatability for separation and determination of carbamates. On a capillary column of 75 microm ID packed with 3 microm octadecyl silica, baseline separation and detection of ten analytes was performed by using a mobile phase consisting of 30% v/v ACN and 70% v/v of 5 mmol/L ammonium acetate (pH 6.5) containing 1 mmol/L SDS and 0.01% triethylamine (TEA). Under the optimum conditions ten carbamate insecticides could be completely separated within 20 min. For the real vegetable samples, an SPE procedure for the cleanup of matrices was carried out prior to pCEC analysis. The detection limits of 0.05-1.6 mg/kg for ten carbamates and mean recoveries of 51.3-109.2% for eight kinds of vegetable samples at different concentrations of carbamates with RSD less than 11.4% were obtained, respectively. The proposed method has been proved to be effective in the rapid analysis of carbamate residues in vegetables.