An amorphous NiP?WC composite coating was prepared on a copper substrate by chemical plating. The corrosion resistance of the coating was studied in a NaCl solution with a mass fraction of 3.5% and a 1 mol/L hydrochloric acid solution. The surface morphology, composition, and microstructure of the coating were characterized by scanning electron microscopy (SEM), Energy dispersive spectrometer （EDS）, and X?ray diffraction (XRD). The corrosion resistance of the coating was analyzed by potentiodynamic polarization and impedance spectroscopy. The results show that in a NaCl solution with a mass fraction of 3.5%, the self corrosion potential of NiP?WC coating shifted approximately 111 mV higher as compared to amorphous NiP coating, resulting in a decrease of approximately 68.8% in self corrosion current density and an increase of approximately 6.7 times in charge transfer resistance. Soaking in 1 mol/L hydrochloric acid solution, the corrosion rate of NiP?WC coating decreased by about an order of magnitude compared to NiP coating, indicating that uniformly distributed WC particles can significantly improve the corrosion resistance of amorphous NiP.

The defect detection of non-woven fabrics can help enterprises improve production efficiency and save costs. Due to the local characteristics of the convolution kernel, the object detection algorithms based on CNN lack the global modeling of the image, and the detection effect is not ideal for defect detection with a large range of scale changes. Therefore, a non-woven fabric defect detection method is proposed based on the combination of Swin Transformer and YOLOv5, which encodes and decodes features through its powerful self-attention. The network can obtain a larger receptive field and fully relate to the context. The layered construction based on the feature pyramid of Swin coincides with the design of the neck of YOLOv5. It can help the network predict the target on the multi-scale feature map. On this basis, CBAM attention mechanism is introduced to help the network focus on important information. Through Mosaic and MixUp data augmentation, the data distribution is enriched and the robustness is increased. Finally, the anchor size of the prediction target frame is fine-tuned to make the regression prediction more accurate. The effectiveness of the proposed method is verified on the self-made data set, and the detection performance of non-woven fabrics is improved.

As natural gas accounts for an increasing proportion of energy consumption, how to accurately predict the future natural gas consumption is of great significance to the rational planning of natural gas. For this problem,a short?term natural gas load forecasting model based on wavelet transform and deep learning was proposed. First,the collected natural gas load was decomposed by using different wavelets , and then normalized it.Secondly, the data wes trained and predictd by using the deep learning algorithm Long Short?Term Memory (LSTM); then the predicted data was separately integrated by using wavelet reconstruction.Finally, the average absolute percentage error, average absolute error and root mean square error were used as evaluation indicators to evaluate the prediction results of different wavelets, and the optimal order and number of layers of the optimal wavelet were calculated.The examples show that the 22nd?order 6th layer of Fk wavelet transforms has higher prediction accuracy than other wavelets transforms and direct use of LSTM for prediction.

In order to study the salt precipitation law of the NaCl?Na₂SO₄?H₂O ternary system at a temperature of 298.15 K, the Pitzer model was used to predict and calculate the activity coefficient and solubility of the system, and the variation of the activity coefficients of Na⁺, Cl^- and SO {}_{\mathrm{4}}^{\mathrm{2}-} and the corresponding phase diagram of the ternary system were analyzed. The results show that with the increase of the Na₂SO₄ mass fraction, the activity coefficients of Cl^- and SO {}_{\mathrm{4}}^{\mathrm{2}-} have no obvious change, while the activity coefficient of Na⁺ icreases first and then decreases. When the mass fraction of Na₂SO₄ in the liquid phase is less than 6.8%, the average change rate of the increase in the activity coefficient of Na⁺ is 4.4%. When the mass fraction of Na₂SO₄ in the liquid phase is between 6.8% and 14.9%, the average change rate of decrease in the activity coefficient of Na⁺ is 4.1%, when the mass fraction of Na₂SO₄ in the liquid phase reaches 14.9%, the activity coefficient of Na⁺ decreases fastest, and the average change rate is 8.0%; when the mass fraction of NaCl in the liquid phase is greater than 22.9% and the mass fraction of Na₂SO₄ is less than 6.8% ,as the water evaporates, NaCl precipitates first and Na₂SO₄ precipitates later; when the liquid phase mass fraction of NaCl is 14.0%～22.9% and the mass fraction of Na₂SO₄ is 6.8%～14.9%, the precipitation order is reversed.