Under the international background of the transformation and promotion of manufacturing, the Chinese government proposed the “Made in China 2025” strategy, which focused on the improvement of a quality-based innovation ability. Moreover, predicting manufacturing quality is one of the crucial measures for quality management. Accurate prediction is closely related to the feature learning of manufacturing processes. Therefore, two categories of intelligent learning approaches, i.e., shallow learning and deep learning, are investigated and compared for manufacturing quality prediction in this paper. Specifically, the feed forward neural network (FFNN) with one hidden layer and the least squares support vector machine (LSSVM) with no hidden layers are selected as the representatives for shallow learning, and the deep restricted Boltzmann machine (DRBM) and the stack autoencoder (SAE) are chosen as the representatives for deep learning. The manufacturing data is collected from a competition about manufacturing quality control in the Tianchi Data Lab of China. The experiments show that the deep framework overwhelms the shallow architecture in terms of mean absolute percentage error, root-mean-square error, and threshold statistics. In addition, the prediction results also indicate that the performances depend on the length of the training data. That is, the bigger the sample size is, the better the performance is.

The preparation of refractory tungsten and tungsten alloys has always been challenging due to their inherent properties. Selective laser melting (SLM) offers a choice for preparing tungsten and tungsten alloys. In this work, 90W-7Ni-3Fe samples were prepared by selective laser melting and investigated. Different process parameter combinations were designed according to the Taguchi method, and volumetric energy density (VED) was defined. Subsequently, the effects of process parameters on densification, phase composition, microstructure, tensile properties, and microhardness were investigated. Nearly a full densification sample (≥99%) was obtained under optimized process parameters, and the value of VED was no less than 300 J/mm³. Laser power had a dominant influence on densification behavior compared with other parameters. The main phases of 90W-7Ni-3Fe are W and γ-(Ni-Fe), dissolved with partial W. In addition, 90W-7Ni-3Fe showed a high tensile strength (UTS = 1121 MPa) with poor elongation (400 HV_0.3) was obtained, but the microhardness presented a fluctuation along building direction due to the inhomogeneous microstructure.

The effect of compound fields of ultrasonic vibration and applied pressure (UV+AP) on three-dimensional (3D) microstructure and tensile properties of recycled Al-Cu-Mn-Fe-Si alloys was systematically studied using conventional two-dimensional (2D) microscopy, synchrotron X-ray tomography, and tensile test. The properties of UV+AP treated alloys with the pouring temperature of 740, 710 and 680 °C were compared when those alloys achieved after gravity casting. After UV+AP treatment, the alloy with pouring temperature of 710 °C show the smallest grain size. Also, the sizes of Fe-rich phases and Al₂Cu are greatly reduced and their 3D morphologies are compacted. The mechanical properties of UV+AP treated alloys are relatively higher than those measured for gravity cast equivalents. This improvement can be explained by the synergistic effect of acoustic cavitation, acoustic streaming, and force-feeding, which resulted in the dendrite fragmentation, uniform solute distribution, and microstructural refinement. The Orowan strengthening and solution strengthening were identified as the main strengthening mechanisms.

All equipment must be maintained during its lifetime to ensure normal operation. Maintenance is one of the critical roles in the success of manufacturing enterprises. This paper proposed a preventive maintenance period optimization model (PMPOM) to find an optimal preventive maintenance period. By making use of the advantages of particle swarm optimization (PSO) and cuckoo search (CS) algorithm, a hybrid optimization algorithm of PSO and CS is proposed to solve the PMPOM problem. The test functions show that the proposed algorithm exhibits more outstanding performance than particle swarm optimization and cuckoo search. Experiment results show that the proposed algorithm has advantages of strong optimization ability and fast convergence speed to solve the PMPOM problem.