A Hybrid Deep Learning and Machine Learning-Based Approach to Classify Defects in Hot Rolled Steel Strips for Smart Manufacturing

Smart manufacturing is a process that optimizes factory performance and production quality by utilizing various technologies including the Internet of Things(IoT)and artificial intelligence(AI).Quality control is an important part of today’s smart manufacturing process,effectively reducing costs and enhancing operational efficiency.As technology in the industry becomes more advanced,identifying and classifying defects has become an essential element in ensuring the quality of products during the manufacturing process.In this study,we introduce a CNN model for classifying defects on hot-rolled steel strip surfaces using hybrid deep learning techniques,incorporating a global average pooling(GAP)layer and a machine learning-based SVM classifier,with the aim of enhancing accuracy.Initially,features are extracted by the VGG19 convolutional block.Then,after processing through the GAP layer,the extracted features are fed to the SVM classifier for classification.For this purpose,we collected images from publicly available datasets,including the Xsteel surface defect dataset(XSDD)and the NEU surface defect(NEU-CLS)datasets,and we employed offline data augmentation techniques to balance and increase the size of the datasets.The outcome of experiments shows that the proposed methodology achieves the highest metrics score,with 99.79%accuracy,99.80%precision,99.79%recall,and a 99.79%F1-score for the NEU-CLS dataset.Similarly,it achieves 99.64%accuracy,99.65%precision,99.63%recall,and a 99.64%F1-score for the XSDD dataset.A comparison of the proposed methodology to the most recent study showed that it achieved superior results as compared to the other studies.

Crystal plasticity finite element simulations on extruded Mg-10Gd rod with texture gradient

The mechanical properties of an extruded Mg-10Gd sample, specifically designed for vascular stents, are crucial for predicting its behavior under service conditions. Achieving homogeneous stresses in the hoop direction, essential for characterizing vascular stents, poses challenges in experimental testing based on standard specimens featuring a reduced cross section. This study utilizes an elasto-visco-plastic self-consistent polycrystal model(ΔEVPSC) with the predominant twinning reorientation(PTR) scheme as a numerical tool, offering an alternative to mechanical testing. For verification, various mechanical experiments, such as uniaxial tension, compression, notched-bar tension, three-point bending, and C-ring compression tests, were conducted. The resulting force vs. displacement curves and textures were then compared with those based on the ΔEVPSC model. The computational model's significance is highlighted by simulation results demonstrating that the differential hardening along with a weak strength differential effect observed in the Mg-10Gd sample is a result of the interplay between micromechanical deformation mechanisms and deformation-induced texture evolution. Furthermore, the study highlights that incorporating the axisymmetric texture from the as-received material incorporating the measured texture gradient significantly improves predictive accuracy on the strength in the hoop direction. Ultimately, the findings suggest that the ΔEVPSC model can effectively predict the mechanical behavior resulting from loading scenarios that are impossible to realize experimentally, emphasizing its valuable contribution as a digital twin.

Flower morphology of Allium(Amaryllidaceae)and its systematic significance

Allium is a complicated genus that includes approximately 1000 species.Although its morphology is well studied,the taxonomic importance of many morphological traits,including floral traits,are poorly understood.Here,we examined and measured the floral characteristics of 87 accessions of 74 Allium taxa(belonging to 30 sections and nine subgenera)from Central to Eastern Asian countries.We then examined the taxonomic relationships between select flower characteristics and a phylogenetic tree based on ITS sequences.Our results confirm that floral morphology provides key taxonomic information to assess species delimitation in Allium.We found that perianth color is an important characteristic within the subg.Melanocrommyum,Polyprason,and Reticulatobulbosa.In subg.Allium,Cepa,and Rhizirideum,significant characteristics include ovary shape,perianth shape,and inner tepal apex.For species in subg.Angunium,the key taxonomic character is ovule number(only one ovule in per locule).In the subg.Allium,Cepa,Polyprason,and Reticulatobulbosa,which belong to the third evolutionary line of Allium,hood-like appendages occur in the ovary,although these do not occur in subg.Rhizirideum.Our results also indicated that the flower morphology of several species in some sections are not clearly distinguished,e.g.,sect.Sacculiferum(subg.Cepa)and sect.Tenuissima(subg.Rhizirideum).This study provides detailed photographs and descriptions of floral characteristics and information on general distributions,habitats,and phenology of the studied taxa.

Analysis of Differences in Electrochemical Performance Between Coin and Pouch Cells for Lithium-Ion Battery Applications

Small coin cell batteries are predominantly used for testing lithium-ion batteries(LIBs)in academia because they require small amounts of material and are easy to assemble.However,insufficient attention is given to difference in cell performance that arises from the differences in format between coin cells used by academic researchers and pouch or cylindrical cells which are used in industry.In this article,we compare coin cells and pouch cells of different size with exactly the same electrode materials,electrolyte,and electrochemical conditions.We show the battery impedance changes substantially depending on the cell format using techniques including Electrochemical Impedance Spectroscopy(EIS)and Galvanostatic Intermittent Titration Technique(GITT).Using full cell NCA-graphite LIBs,we demonstrate that this difference in impedance has important knock-on effects on the battery rate performance due to ohmic polarization and the battery life time due to Li metal plating on the anode.We hope this work will help researchers getting a better idea of how small coin cell formats impact the cell performance and help predicting improvements that can be achieved by implementing larger cell formats.

Benefit in physical function and quality of life to nonsurgical treatment of varicose veins: Pilot study

BACKGROUND Studies on varicose veins have focused its effects on physical function;however,whether nonsurgical treatments alter muscle oxygenation or physical function remains unclear.Moreover,the differences in such functions between individuals with varicose veins and healthy individuals remain unclear.AIM To investigate changes in physical function and the quality of life(QOL)following nonsurgical treatment of patients with varicose veins and determine the changes in their muscle oxygenation during activity.METHODS We enrolled 37 participants(those with varicose veins,n=17;healthy individuals,n=20).We performed the following measurements pre-and post-nonsurgical treatment in the varicose vein patients and healthy individuals:Calf muscle oxygenation during the two-minute step test,open eyes one-leg stance,30 s sit-to-stand test,visual analog scale(VAS)for pain,Pittsburgh sleep quality index,physical activity assessment,and QOL assessment.RESULTS Varicose veins patients and healthy individuals differ in most variables(physical function,sleep quality,and QOL).Varicose veins patients showed significant differences between pre-and post-nonsurgical treatment—results in the 30 sit-to-stand test[14.41(2.45)to 16.35(4.11),P=0.018],two-minute step test[162.29(25.98)to 170.65(23.80),P=0.037],VAS for pain[5.35(1.90)to 3.88(1.73),P=0.004],and QOL[39.34(19.98)to 26.69(17.02),P=0.005];however,no significant difference was observed for muscle oxygenation.CONCLUSION Nonsurgical treatment improved lower extremity function and QOL in varicose veins patients,bringing their condition close to that of healthy individuals.Future studies should include patients with severe varicose veins requiring surgery to confirm our findings.

激光熔覆含B_4C_p,SiC_p钴基合金涂层的组织与耐磨性能

运用激光熔覆技术在16Mn钢表面制备了钴基合金涂层(Co55)、含20%SiCp(体积分数,下同)的钴基合金涂层(CoSiC)以及含20%B4Cp钴基合金涂层(CoB4C),比较研究了合金涂层的组织、相结构、显微硬度及滑动磨损性能。结果表明:合金涂层由涂层结合区的胞状共晶组织及涂层区的树枝状亚共晶组织组成,CoSiC涂层及CoB4C涂层的树枝晶比Co55涂层的更细小;B4Cp及SiCp在熔覆过程中完全熔解,其分解出的B,C,Si与涂层中的合金元素结合形成了更多的化合物,Co55涂层由γ Co和(Cr,Fe)7C3组成,CoSiC涂层由γ Co,Cr7C3,Cr23C6,CoSi2,Cr3Si和Si2W组成,CoB4C涂层由γ Co,Cr7C3,Cr23C6,CrB,CrB2和Fe23(C,B)6组成;3种激光熔覆涂层的显微硬度及耐磨性由高到低的顺序为CoB4C→CoSiC→Co55。对涂层的强化机理进行了分析。

多元醇法制备CoNi纳米粒子的形成机制,尺寸控制及磁性能

采用多元醇法在150～190℃合成了CoNi合金纳米粒子,利用SEM-EDX,XRD和VSM对所制备的CoNi纳米粒子形貌、成分、结构以及磁性能进行了研究,并进一步探讨了形核剂K2PtCl4对CoNi纳米粒子形貌及磁性能的影响。结果表明,在180℃用多元醇法制备的Co40Ni60(inat%)纳米粒子为FCC结构,Co2+要易于Ni2+被还原,导致最初10min内合成的CoNi纳米粒子中含有约78%(原子分数)Co,表现为高饱和磁化强度和高矫顽力,随着反应时间的延长,CoNi纳米粒子的Co含量、饱和磁化强度及矫顽力逐步下降。在150～190℃范围内,随着反应温度的提高,Ni2+的被还原能力增强,高温下合成的CoNi纳米粒子具有较低的饱和磁化强度和较小的矫顽力。形核剂K2PtCl4的加入,并不影响CoNi合金纳米粒子的成分和晶体结构。但是,随着形核剂浓度的增加,CoNi纳米粒子平均直径明显减小,其矫顽力有所增大。通过设计形核剂的浓度,CoNi纳米粒子的直径可以在96～580nm范围内任意控制。

Development of practical postprocessor for 5-axis machine tool with non-orthogonal rotary axes

In order to develop a practical postprocessor for 5-axis machine tool,the general equations of numerically controlled(NC) data for 5-axis configurations with non-orthogonal rotary axes were exactly expressed by the inverse kinematics,and a windows-based postprocessor written with Visual Basic was developed according to the proposed algorithm.The developed postprocessor is a general system suitable for all kinds of 5-axis machines with orthogonal and non-orthogonal rotary axes.Through implementation of the developed postprocessor and verification by a cutting simulation and machining experiment,the effectiveness of the proposed algorithm is confirmed.Compatibility is improved by allowing exchange of data formats such as rotational total center position(RTCP) controlled NC data,vector post NC data,and program object file(POF) cutter location(CL) data,and convenience is increased by adding the function of work-piece origin offset.Consequently,a practical post-processor for 5-axis machining is developed.

Optimal rotor wear design in hypotrochoidal gear pump using genetic algorithm

The wear rate between the rotors of a hypotrochoidal gear pump is characterized.Using the knowledge of shape design on the rotors,the contact stresses without hydrodynamic effect between the rotor teeth were evaluated through the calculation of the Hertzian contact stress.Based on the above results and the sliding velocity between the rotors,a genetic algorithm (GA) was used as an optimization technique forminimizing the wear rate proportional factor (WRPF).The result shows that the wear rate or the WRPF can be reduced considerably,e.g.approximately 12.8%,throughout the optimization using GA.

Numerical Simulation of Continuous Tension Leveling Process of Thin Strip Steel and Its Application

Cold-rolled thin strip steel of high flatness quality undergoes multistage deformation during tension leveling. Thus, the parameters of set-up and manipulating are more difficult. With the aid of FE code MSC. MARC, the tension leveling process of thin strip steel was numerically simulated. Concentrating on the influence of the roll intermeshes in 2# anti-cambering on the distribution and magnitude of residual stresses in leveled strip steel, several experiments were clone with the tension leveler based on the results from the simulation. It was found from the simulation that the magnitude of longitudinal residual stresses in the cross-section of the leveled strip steel regularly presents obvious interdependence with the roll intermeshes in 2# anti-cambering. In addition, there is a steady zone as the longitudinal residual stresses of the surface layers in leveled strip steel vary with the roll intermeshes of 2# anticambering, which is of importance in the manipulation of tension levelers. It was also found that the distribution of strains and stresses across the width of strip steel is uneven during leveling or after removing the tension loaded upon the strip, from which it was found that 3D simulation could not be replaced by 2D analysis because 2D analysis in this case cannot represent the physical behavior of strip steel deformation during tension leveling.

Thermal stability and mechanical properties of thick thermal barrier coatings with vertical type cracks

The thermal stability and failure mechanism of thick thermal barrier coatings(TBCs) with and without vertical type cracks were investigated through the cyclic thermal exposure and thermal-shock tests. The TBC systems with thickness of about 2000 μm in the top coat were prepared by an air plasma spray(APS) on the bond coat of about 150 μm in thickness prepared by APS. The adhesive strength values of the as-prepared TBCs with and without vertical type cracks were determined to be 24.7 and 11.0 MPa, respectively, indicating the better interface stability in the TBC with vertical type cracks. The TBC with vertical type cracks shows a better thermal durability than that without vertical type cracks in the thermal cyclic exposure and thermal-shock tests. The hardness values of the as-prepared TBCs with and without vertical type cracks were found to be 6.6 and 5.3 GPa, respectively, which were increased to 9.5 and 5.5 GPa, respectively, after the cyclic thermal exposure tests. These results indicate that the vertical type cracks developed in the top coat are important in improving the lifetime performance of thick TBC in high temperature environment.

Lightweight design of 45000r/min spindle using full factorial design and extreme vertices design methods

Factors for determining the spindle size are the shaft diameter, positions of bearing and motor, and entire length of the spindle. Then, it is important to find the assembling of the optimal design variables, which satisfy the stiffimss and rotational speed required to the spindle. A general full factorial design method was used to verify some factors that affect the natural frequency of a spindle. It is verified that the shorter shaft length and bearing span length represent the higher natural frequency, and there are some effects according to the change in the levels of factors. The detailed spindle dimension is determined by applying an EVD method, which can define the optimal bearing position through considering the limiting condition. Based on the estimated regression model, the optimal spindle size and bearing distance that can improve the primary natural frequency are obtained, and the influence of design factors on the natural frequency is also analyzed.

Pendulation reduction on ship-mounted container crane via T-S fuzzy model

Ship-mounted container cranes are challenging industrial applications of nonlinear pendulum-like systems with oscillating disturbance which can cause them unstable.Since wave-induced ship motion causes the hoisted container to swing during the transfer operation,the swing motion may be dangerously large and the operation must be stopped.In order to reduce payload pendulation of ship-mounted crane,nonlinear dynamics of ship-mounted crane is derived and a control method using T-S fuzzy model is proposed.Simulation results are given to illustrate the validity of the proposed design method and pendulation of ship-mounted crane is reduced significantly.

Realization of orientation interpolation of 6-axis articulated robot using quaternion

In general, the orientation interpolation of industrial robots has been done based on Euler angle system which can result in singular point （so-called Gimbal Lock）. However, quaternion interpolation has the advantage of natural （specifically smooth） orientation interpolation without Gimbal Lock. This work presents the application of quatemion interpolation, specifically Spherical Linear IntERPolation （SLERP）, to the orientation control of the 6-axis articulated robot （RS2） using LabVIEW and RecurDyn. For the comparison of SLERP with linear Euler interpolation in the view of smooth movement （profile） of joint angles （torques）, the two methods are dynamically simulated on RS2 by using both LabVIEW and RecurDyn. Finally, our original work, specifically the implementation of SLERP and linear Euler interpolation on the actual robot, i.e. RS2, is done using LabVIEW motion control tool kit. The SLERP orientation control is shown to be effective in terms of smooth joint motion and torque when compared to a conventional （linear） Euler interpolation.

Fluid flow and heat transfer characteristics of spiral coiled tube: Effects of Reynolds number and curvature ratio

Numerical analysis was performed to investigate flow and heat transfer characteristics in spiral coiled tube heat exchanger. Radius of curvature of the spiral coiled tube was gradually increased as total rotating angle reached 12n. As the varying radius of curvature became a dominant flow parameter, three-dimensional flow analysis was performed to this flow together with different Reynolds numbers while constant wall heat flux condition was set in thermal field. From the analysis, centrifugal force due to curvature effect is found to have significant role in behavior of pressure drop and heat transfer. The centrifugal force enhances pressure drop and heat transfer to have generally higher values in the spiral coiled tube than those in the straight tube. Even then, friction factor and Nusselt number are found to follow the proportionality with square root of the Dean number. Individual effect of flow parameters of Reynolds number and curvature ratio was investigated and effect of Reynolds number is found to be stronger than that of curvature effect.

Torsional vibration analysis of lathe spindle system with unbalanced workpiece

For the purpose of analyzing the torsional vibration caused by the gravitational unbalance torque arisen in a spindle system when it is machining heavy work piece,a 10-DOF lumped parameter model was made for the machine tool spindle system with geared transmission.By using the elementary method and Runge-Kutta method in Matlab,the eigenvalue problem was solved and the pure torsional vibration responses were obtained and examined.The results show that the spindle system cannot operate in the desired constant rotating speed as far as the gravitational unbalance torque is engaged,so it may cause bad effect on machining accuracy.And the torsional vibration increases infinitely near the resonant frequencies,so the spindle system cannot operate normally during these spindle speed ranges.

Fourier and wavelet transformations application to fault detection of induction motor with stator current

Fault detection of an induction motor was carried out using the information of the stator current. After synchronizing the actual data, Fourier and wavelet transformations were adopted in order to obtain the sideband or detail value characteristics under healthy and various faulty operating conditions. The most reliable phase current among the three phase currents was selected using an approach that employs the fuzzy entropy measure. Data were trained with a neural network system, and the fault detection algorithm was verified using the unknown data. Results of the proposed approach based on Fourier and wavelet transformations indicate that the faults can be properly classified into six categories. The training error is 5.3×10-7, and the average test error is 0.103.

Effects of electrolytes variation on formation of oxide layers of 6061 Al alloys by plasma electrolytic oxidation

Plasma electrolytic oxidation(PEO) processes were carried out to produce ceramic layers on 6061 aluminum substrates in four kinds of electrolytes such as silicate and aluminate solution with and without sodium fluorosilicate.The PEO processes were carried out under a hybrid voltage(260 V DC combined with 200 V,60 Hz AC amplitude) at room temperature for 5 min.The composition,microstructure and element distribution analyses of the PEO-treated layers were carried out by XRD and SEM & EDS.The effect of the electrolyte contents on the growth mechanism,element distribution and properties of oxide layers were studied.It is obvious that the layers generated in aluminate solutions show smoother surfaces than those in silicate solutions.Moreover,an addition of fluorine ion can effectively control the layer porosity;therefore,it can enhance the properties of the layers.

Influence of alloying elements on microstructure and microhardness of Mg-Sn-Zn-based alloys

The phase evolution in （88%-91%）Mg-8%Sn-l%Zn-X （X=A1, Mn and/or Ce） system was analyzed via CALPHAD method and simulations were used in precise selection of the chemical composition. The influence of the addition of different alloying elements such as A1, Mn and Ce on the microstructure and microhardness of Mg-8%Sn-l%Zn-based alloys was investigated. Combined addition of A1 and Mn shows features distinct from separate addition of A1 or Mn. Additions of l%AI and l%Mn to base alloy result in the formation of massive A1-Mn phase in a-Mg matrix grains. Addition of Ce element can refme the second eutectic precipitates and form intermetallic compounds with Sn. Fine rod-like Sn-Ce phase presents mainly on the grain boundaries and plays a role in inhibiting grain growth. The effects of alloying elements on Vickers microhardness and indentation size effect of base alloy were examined.

Power interconnected system clustering with advanced fuzzy C-mean algorithm

An advanced fuzzy C-mean （FCM） algorithm was proposed for the efficient regional clustering of multi-nodes interconnected systems. Due to various locational prices and regional coherencies for each node and point, modified similarity measure was considered to gather nodes having similar characteristics. The similarity measure was needed to contain locafi0nal prices as well as regional coherency. In order to consider the two properties simultaneously, distance measure of fuzzy C-mean algorithm had to be modified. Regional clustering algorithm for interconnected power systems was designed based on the modified fuzzy C-mean algorithm. The proposed algorithm produces proper classification for the interconnected power system and the results are demonstrated in the example of IEEE 39-bus interconnected electricity system.