Flexible job-shop scheduling problem (FJSP) is a new research hotspot in the field of production scheduling. To solve the multiobjective FJSP problem, the production of flexible job shop can run ...normally and quickly. This research takes into account various characteristics of FJSP problems, such as the need to ensure the continuity and stability of processing, the existence of multiple objectives in the whole process, and the constant complexity of changes. It starts with deep learning neural networks and genetic algorithms. Long short-term memory (LSTM) and convolutional neural networks (CNN) are combined in deep learning neural networks. The new improved algorithm is based on the combination of deep learning neural networks LSTM and CNN with genetic algorithm (GA), namely, CNN-LSTM-GA algorithm. Simulation results showed that the accuracy of the CNN-LSTM-GA algorithm was between 85.2% and 95.3% in the test set. In the verification set, the minimum accuracy of the CNN-LSTM-GA algorithm was 84.6%, both of which were higher than the maximum accuracy of the other two algorithms. In the FJSP simulation experiment, the AUC value of the CNN-LSTM-GA algorithm was 0.92. After 40 iterations, the F1 value of the CNN-LSTM-GA algorithm remained above 0.8, which was significantly higher than the other two algorithms. CNN-LSTM-GA is superior to the other two algorithms in terms of prediction accuracy and overall performance of FJSP. It is more suitable for solving the discrete manufacturing job scheduling problem with FJSP characteristics. This study significantly raises the utilisation rate of the assembly shop’s equipment, optimises the scheduling of FJSP, and fully utilises each processing device’s versatile characteristics, which are quite useful for the production processes of domestic vehicle manufacturing companies.
•Orthogonal design was combined with ideal overlap model to ascertain key parameters.•Cooling rate and solidification velocity were the reason for morphological features.•The influence rules of ...critical parameters on morphology and properties were deduced.•The characteristics of morphology determine the anisotropy of mechanical properties.
Laser Metal Deposition Shaping (LMDS) is a new rapid manufacturing technology, which can build fully-dense metal components directly from the information transferred from a computer file by depositing metal powders layer by layer with neither mould nor tool. Typically, performed with stainless steel (SS) 316 powder, the orthogonal experiments combining with the ideal overlapping model were applied to ascertain the optimal processing parameters. Then the characteristics of microstructure, composition and phase of as-deposited cladding layers were analyzed through Scanning Electron Microscope (SEM) and X-ray diffraction (XRD), as well as relative model. Furthermore, the cooling rate and the solidification velocity during LMDS were evaluated based on empirical method. With the optimal parameters, some parts were fabricated without obvious defects, and then the mechanical properties of them were tested. Finally, the influencing regularities of critical parameters on microstructure and properties were concluded by comparison. The results prove that the microstructure of SS 316 deposits is composed of the slender dendrites growing epitaxially from the substrate, the mechanical properties are favorable and anisotropic, and the composition is uniform. Besides, the microstructure morphology and the mechanical properties are affected by the varied processing parameters at different degrees. Among them, the scanning speed shows the most remarkable effects on microstructure morphology, characteristic microscale, mechanical properties, as well as geometric shape of as-deposited parts.
Laser additive direct deposition of metals is a new rapid manufacturing technology, which combines with computer-aided design (CAD), laser cladding and rapid prototyping. The advanced technology can ...build fully dense metal components directly from CAD files with neither mould nor tool. Based on the theory of this technology, a promising rapid manufacturing system called “Laser Metal Deposition Shaping (LMDS)” has been constructed and developed successfully by Chinese Academy of Sciences, Shenyang Institute of Automation. Through the LMDS system, comprehensive experiments are carried out with nickel-based superalloy to systematically investigate the influences of the processing parameters on forming characteristics. By adjusting to the optimal processing parameters, fully dense and near-net-shaped metallic parts can be directly obtained through melting coaxially fed powder with a laser. Moreover, the microstructure and mechanical properties of as-formed samples are tested and analyzed synthetically. As a result, significant processing flexibility with the LMDS system over conventional processing capabilities is recognized, with potentially lower production cost, higher quality components, and shorter lead-time.
Mechanical equipment fault detection is critical in industrial applications. Based on vibration signal processing and analysis, the traditional fault diagnosis method relies on rich professional ...knowledge and artificial experience. Achieving accurate feature extraction and fault diagnosis is difficult using such an approach. To learn the characteristics of features from data automatically, a deep learning method is used. A qualitative and quantitative method for rolling bearing faults diagnosis based on an improved convolutional deep belief network (CDBN) is proposed in this study. First, the original vibration signal is converted to the frequency signal with the fast Fourier transform to improve shallow inputs. Second, the Adam optimizer is introduced to accelerate model training and convergence speed. Finally, the model structure is optimized. A multi-layer feature fusion learning structure is put forward wherein the characterization capabilities of each layer can be fully used to improve the generalization ability of the model. In the experimental verification, a laboratory self-made bearing vibration signal dataset was used. The dataset included healthy bearings, nine single faults of different types and sizes, and three different types of composite fault signals. The results of load 0 kN and 1 kN both indicate that the proposed model has better diagnostic accuracy, with an average of 98.15% and 96.15%, compared with the traditional stacked autoencoder, artificial neural network, deep belief network, and standard CDBN. With improved diagnostic accuracy, the proposed model realizes reliable and effective qualitative and quantitative diagnosis of bearing faults.
Rust fungi secrete various specialized effectors into host cells to manipulate the plant defense response. Conserved motifs, including RXLR, LFLAK-HVLVxxP (CRN), Y/F/WxC, CFEM, LysM, EAR, ...SG-P-C-KR-P, DPBB_1 (PNPi), and ToxA, have been identified in various oomycete and fungal effectors and are reported to be crucial for effector translocation or function. However, little is known about potential effectors containing any of these conserved motifs in the wheat leaf rust fungus (
Puccinia triticina
,
Pt
). In this study, sequencing was performed on RNA samples collected from the germ tubes (GT) of uredospores of an epidemic
Pt
pathotype PHTT(P) and
Pt
-infected leaves of a susceptible wheat cultivar “Chinese Spring” at 4, 6, and 8 days post-inoculation (dpi). The assembled transcriptome data were compared to the reference genome of “
Pt
1-1 BBBD Race 1.” A total of 17,976 genes, including 2,284 “novel” transcripts, were annotated. Among all these genes, we identified 3,149 upregulated genes upon
Pt
infection at all time points compared to GT, whereas 1,613 genes were more highly expressed in GT. A total of 464 secreted proteins were encoded by those upregulated genes, with 79 of them also predicted as possible effectors by EffectorP. Using hmmsearch and Regex, we identified 719 RXLR-like, 19 PNPi-like, 19 CRN-like, 138 Y/F/WxC, and 9 CFEM effector candidates from the deduced protein database including data based on the “
Pt
1-1 BBBD Race 1” genome and the transcriptome data collected here. Four of the PNPi-like effector candidates with DPBB_1 conserved domain showed physical interactions with wheat NPR1 protein in yeast two-hybrid assay. Nine Y/F/WxC and seven CFEM effector candidates were transiently expressed in
Nicotiana benthamiana
. None of these effector candidates showed induction or suppression of cell death triggered by BAX protein, but the expression of one CFEM effector candidate, PTTG_08198, accelerated the progress of cell death and promoted the accumulation of reactive oxygen species (ROS). In conclusion, we profiled genes associated with the infection process of the
Pt
pathotype PHTT(P). The identified effector candidates with conserved motifs will help guide the investigation of virulent mechanisms of leaf rust fungus.
•Ultrasonic vibratory stress relief (UVSR) was first applied to a random size plate.•The local yield stress of AA6082 is reduced by at least 27% during the UVSR.•The vibratory stress introduced by ...ultrasonic vibration was obtained accurately.•The stress relief ratio was 53% and the distribution interval was reduced by 57%.
Ultrasonic vibratory stress relief (UVSR) is a novel method for residual stress relieving of metal parts. In this paper, the UVSR method was applied to treat a random-sized plate, which is not designed to match with the resonant frequency of the ultrasonic transducer. The UVSR system includes an ultrasonic generator, a 20 kHz ultrasonic transducer and specially designed fixtures to exert ultrasonic vibration to the treated parts. Based on the experimental results, the average stress relief ratio reached 53% and the final residual stress distribution interval was reduced by 57. The vibratory stress introduced by the ultrasonic vibration was obtained accurately by matching the FE model with the measured vibration amplitude distribution. It is found that local yield stress, instead of macroscopic yield stress, should be used as the threshold of residual stress relieving. Moreover, if the local yield stress of a material is constant, the local yield stress of 6082 aluminum alloy is reduced by at least 27% during the UVSR. Finally, it is found that the residual stress relief rate in one direction is proportional to the vibratory stress introduced in that direction.
Abstract
In order to solve the problem that the material utilization rate of soluble magnesium base alloy rod is less than 30%, the method of magnesium alloy rod casting is adopted to improve the ...material utilization rate. However, the cooling mode affects the dissolution rate of soluble magnesium alloy after casting. According to the different thermal conductivity of different materials, cylindrical graphite molds and copper molds with diameters of 5mm and 40mm are selected for casting magnesium alloys. In order to ensure the reliability of experimental results, polarization method and weight loss method were used to analyze the dissolution rate of soluble magnesium base alloy under different cooling modes. The test results show that: Magnesium alloy is cooled and solidified by copper mold with a diameter of 5mm, and the dissolution rate is the highest in 1.5% NaCl solution with a speed of 1.2856mm/h. The grain size of magnesium alloy can be refined by increasing cooling rate. After the grain boundary of magnesium-based alloy is refined, the grain boundary between the alloy increases, the number of corrosion galvanic cells increases, and the dissolution rate of magnesium-based alloy gradually increases.
The surface characteristics and microstructure of a 100-oriented single crystal superalloy subjected to ultrasonic shot peening (USP) were investigated as a function of peening duration. The obtained ...results show that USP significantly increases the surface microhardness of the single crystal superalloy, reaching up to 650 HV. As peening duration increases, surface roughness and microhardness increase at first and then remain stable. Meanwhile, new components and orientations are formed on the treated surface. The depths of the cold work layer and slip band reach saturation with sufficient peening durations. However, the microstructure beneath the surface continues to evolve with increasing peening time. Excessive peening duration will facilitate the formation of curved slip bands, distinct misorientation and subgrains, which may damage the coherent strengthening of γ/γ′ structures and result in a lower hardness value in the depth direction. Combining the effects of surface alloying, strain-induced diffusion and strain-induced dissolution, four layers (i.e., the nanocrystalline α-Fe layer, Fe, Ti, Ni interdiffusion layer, nickel-based γ′-free layer and deformed γ/γ′ layer) are formed on a single crystal substrate with sufficient USP durations. For single crystal superalloys, there exists an optimal processing duration to achieve the balance between surface hardening and coherent strengthening of γ/γ′ structures.
Display omitted
•A 100-oriented SX superalloy was ultrasonic shot peened with 2–60 min.•With peening duration increase, deformed layer depth is saturated, while microstructures continue to evolve.•Optimum duration is 2–4 min for SX to enhance the surface hardness and keep γ/γ′ structures integrity.•Excessive duration will damage the γ/γ′ structures, cause distinct misorientations and lead to the lower hardness with depth.•By USP, nanocrystalline α-Fe, interdiffusion, Ni-based γ′-free and deformed γ/γ′ layers are formed on SX substrate.