Water quality guarantee in remote areas necessitates the development of portable, sensitive, fast, cost-effective, and easyto-use water quality detection methods. The current work reports on a microfluidic paper-based analytical device (μPAD) integrated with a smartphone app for the simultaneous detection of cross-type water quality parameters including pH, Cu(II), Ni(II), Fe(III), and nitrite. The shapes, baking time, amount, and ratios of reaction reagent mixtures of wax μPAD were optimized to improve the color uniformity and intensity effectively. An easy-to-use smartphone app was established for recording, analyzing, and directly reading the colorimetric signals and target concentrations on μPAD. The results showed that under the optimum conditions, the current analytical platform has reached the detection limits of 0.4, 1.9, 2.9, and 1.1 ppm for nitrite, Cu(II), Ni(II), and Fe(III), respectively, and the liner ranges are 2.3−90 ppm (nitrite), 3.8−400 ppm (Cu(II)), 2.9−1000 ppm (Ni(II)), 2.8−500 ppm (Fe(III)), and 5−9 (pH). The proposed portable smartphone-app integrated μPAD detection system was successfully applied to real industrial wastewater and river water quality monitoring. The proposed method has great potential for field water quality detection.

Data imbalance and large data probability distribution discrepancies are major factors that reduce the accuracy of remaining useful life (RUL) prediction of high-reliability rotating machinery. In feature extraction, most deep transfer learning models consider the overall features but rarely attend to the local target features that are useful for RUL prediction; insufficient attention paid to local features reduces the accuracy and reliability of prediction. By considering the contribution of input data to the modeling output, a deep learning model that incorporates the attention mechanism in feature selection and extraction is proposed in our work; an unsupervised clustering method for classification of rotating machinery performance state evolution is put forward, and a similarity function is used to calculate the expected attention of input data to build an input data extraction attention module; the module is then fused with a gated recurrent unit (GRU), a variant of a recurrent neural network, to construct an attention-GRU model that combines prediction calculation and weight calculation for RUL prediction. Tests on public datasets show that the attention-GRU model outperforms traditional GRU and LSTM in RUL prediction, achieves less prediction error, and improves the performance and stability of the model.

No abstract

Performance feature extraction is the primary problem in equipment performance degradation assessment. To handle the problem of high-dimensional performance characterization and complexity of calculating the performance indicators in flexible material roll-to-roll processing, this paper proposes a PCA method for extracting the degradation characteristic of roll shaft. Based on the analysis of the performance influencing factors of flexible material roll-to-roll processing roller, a principal component analysis extraction model was constructed. The original feature parameter matrix composed of 10-dimensional feature parameters such as time domain, frequency domain, and time-frequency domain vibration signal of the roll shaft was established; then, we obtained a new feature parameter matrix Z org ∗ by normalizing the original feature parameter matrix. The correlation measure between every two parameters in the matrix Z org ∗ was used as the eigenvalue to establish the covariance matrix of the performance degradation feature parameters. The Jacobi iteration method was introduced to derive the algorithm for solving eigenvalue and eigenvector of the covariance matrix. Finally, using the eigenvalue cumulative contribution rate as the screening rule, we linearly weighted and fused the eigenvectors and derived the feature principal component matrix F of the processing roller vibration signal. Experiments showed that the initially obtained, 10-dimensional features of the processing rollers’ vibration signals, such as average, root mean square, kurtosis index, centroid frequency, root mean square of frequency, standard deviation of frequency, and energy of the intrinsic mode function component, can be expressed by 3-dimensional principal components F 1 , F 2 , and F 3 . The vibration signal features reduction dimension was realized, and F 1 , F 2 , and F 3 contain 98.9% of the original vibration signal data, further illustrating that the method has high precision in feature parameters’ extraction and the advantage of eliminating the correlation between feature parameters and reducing the workload selecting feature parameters.