Ni-based GH625 superalloy has been widely employed in the aerospace industry due to its high strength, outstanding corrosion resistance and high temperature resistance. A novel hybrid processing method of ultrasonic-assisted electrochemical grinding (UAECG) can achieve the high-effective removal rate for difficult-to-process materials and thereby avoids the stray corrosion during the process. This study systematically investigated the electrochemical dissolution behaviors of GH625 alloy at low current density and effects of processing parameters on its surface roughness. A qualitative model was proposed to further reveal its removal mechanism for GH625 alloy during UAECG process. Polarization curves depicted that an efficient and stable electrochemical dissolution was achieved at an appropriate temperature (20℃) and concentration (10 wt.%) of NaNO3 electrolyte. The findings also revealed that selective corrosion preferentially occurred on the grain boundary or near the NbC carbides under different current density corrosion circumstance. Compared with ECG process, the excellent surface quality (Ra = 0.37 μm) and taper of the small holes (taper = 0.04 ± 0.005°) are obtained at the optimized condition of pulse voltage of 5.8V, feed rate of 0.6mm /min, cathode speed of 12kr /min and ultrasonic drive amplitude of 60 % by UAECG technology.

In order to realize real-time and precise monitoring of the tool wear in the milling process, this paper presents a tool wear predictive model based on the Stacked Multilayer Denoising AutoEncoders (SMDAE) technique, the particle swarm optimization with an adaptive learning strategy (PSO-ALS) and the Least Squares Support Vector Machine (LSSVM). Cutting force and vibration information are adopted as the monitoring signals. The unique feature extraction and fusion method consists of three steps: multi-domain features extraction, dimension-reduction by principal component analysis (PCA) and dimension-increment by SMDAE. As a novel feature representation learning approach, the SMDAE technique is utilized to fuse the PCA-based fusion features to enrich the effective information by realizing dimension-increment, thus helping polish up the predictive performance of the proposed model. PSO-ALS is used to obtain the optimal parameters for LSSVM, simplifying the problem and increasing the population diversity. Twelve sets of cutting experiments are conducted to verify the effectiveness of the proposed model. The experimental results show that the presented model is superior to models such as PSO-LSSVM in predictive performance, and the SMDAE technique effectively improves the prediction accuracy of the constructed model. The findings of this paper provide theoretical guidance for monitoring milling tool wear in real industrial situations.

This paper proposes a novel tool wear predicting method based on weighted multi-kernel relevance vector machine (WMKRVM) and the integrated radial basis function-based probabilistic kernel principal component analysis (PKP-CA_IRBF). The proposed WMKRVM model constructs the optimal multi-kernel model by seeking the weight parameter of the optimized single kernel RVM. As a new dimension increment technique, PKPCA_IRBF can extract the noise information of the process data and incorporate the noise information into the model. Moreover, this work first proposes using PKPCA_IRBF to fuse monitoring feature to improve the CI provided by the WMKRVM model. Besides, the parameter selection region and model accuracy of the PKPCA_IRBF are better than the conventional PKPCA_RBF technique, which helps improve the efficiency of model construction. The cutting experiment is conducted to validate the effectiveness of the proposed tool wear predicting technique. Experimental results show that the proposed tool wear predicting technique can accurately monitor the tool wear width with strong robustness under various cutting conditions, laying the foundation for applying to the industrial field.

This paper proposes a novel tool wear predicting method based on weighted multi-kernel relevance vector machine (WMKRVM) and the integrated radial basis function-based probabilistic kernel principal component analysis (PKPCA_IRBF). The proposed WMKRVM model constructs the optimal multi-kernel model by seeking the weight parameter of the optimized single kernel RVM. As a new dimension increment technique, PKPCA_IRBF can extract the noise information of the process data and incorporate the noise information into the model. Moreover, this work first proposes using PKPCA_IRBF to fuse monitoring feature to improve the CI provided by the WMKRVM model. Besides, the parameter selection region and model accuracy of the PKPCA_IRBF are better than the conventional PKPCA_RBF technique, which helps improve the efficiency of model construction. The cutting experiment is conducted to validate the effectiveness of the proposed tool wear predicting technique. Experimental results show that the proposed tool wear predicting technique can accurately monitor the tool wear width with strong robustness under various cutting conditions, laying the foundation for applying to the industrial field.

In order to realize real-time and precise monitoring of the tool wear in the milling process, this paper presents a tool wear predictive model based on the Stacked Multilayer Denoising AutoEncoders (SMDAE) technique, the particle swarm optimization with an adaptive learning strategy (PSO-ALS) and the Least Squares Support Vector Machine (LSSVM). Cutting force and vibration information are adopted as the monitoring signals. The unique feature extraction and fusion method consists of three steps: multi-domain features extraction, dimension-reduction by principal component analysis (PCA) and dimension-increment by SMDAE. As a novel feature representation learning approach, the SMDAE technique is utilized to fuse the PCA-based fusion features to enrich the effective information by realizing dimension-increment, thus helping polish up the predictive performance of the proposed model. PSO-ALS is used to obtain the optimal parameters for LSSVM, simplifying the problem and increasing the population diversity. Twelve sets of cutting experiments are conducted to verify the effectiveness of the proposed model. The experimental results show that the presented model is superior to models such as PSO-LSSVM in predictive performance, and the SMDAE technique effectively improves the prediction accuracy of the constructed model. The findings of this paper provide theoretical guidance for monitoring milling tool wear in real industrial situations.