No abstract

Deep learning methods have been widely used in the field of intelligent fault diagnosis due to their powerful feature learning and classification capabilities. However, it is easy to overfit depth models because of the large number of parameters brought by the multilayer-structure. As a result, the methods with excellent performance under experimental conditions may severely degrade under noisy environment conditions, which are ubiquitous in practical industrial applications. In this paper, a novel method combining a one-dimensional (1-D) denoising convolutional autoencoder (DCAE) and a 1-D convolutional neural network (CNN) is proposed to address this problem, whereby the former is used for noise reduction of raw vibration signals and the latter for fault diagnosis using the de-noised signals. The DCAE model is trained with noisy input for denoising learning. In the CNN model, a global average pooling layer, instead of fully-connected layers, is applied as a classifier to reduce the number of parameters and the risk of overfitting. In addition, randomly corrupted signals are adopted as training samples to improve the anti-noise diagnosis ability. The proposed method is validated by bearing and gearbox datasets mixed with Gaussian noise. The experimental result shows that the proposed DCAE model is effective in denoising and almost causes no loss of input information, while the using of global average pooling and input-corrupt training improves the anti-noise ability of the CNN model. As a result, the method combined the DCAE model and the CNN model can realize high-accuracy diagnosis even under noisy environment.

No abstract

Recent developments in Fourier transform infrared spectroscopy-partial least squares (FTIR-PLSs) extend the application of this strategy to the field of the edible oils and fats research. In this work, FT-IR spectroscopy was used as an effective analytical tool to determine the peroxide value of virgin walnut oil (VWO) samples undergone during heating. The spectra were recorded from a film of pure oil between two disks of KBr for each sample at frequency regions of 4000–650 cm−1. Changes in the values of the frequency of most of the bands of the spectra were observed and used to build the calibration model. PLS model correlates the actual and FT-IR estimated value of peroxide value with a correlation coefficient of 0.99, and the root mean square error of the calibration (RMSEC) value is 0.4838. The methodology has potential as a fast and accurate way for the quantification of peroxide value of the edible oils.

No abstract