高稳高效海上风电安装平台关键制造技术研究

海上风电作为可再生清洁能源之一,受到世界各国的高度重视与大力发展。我国将海上风电提升至解决能源危机、减缓气候变化、调整能源结构的国家战略高度,到2030年我国单位国内生产总值二氧化碳排放将比2005年下降65%以上,非化石能源占一次能源消费比重将达到25%左右。安装平台不足将是我国海上风电场无法如期建成投产的主要障碍。对自升自航式海上风电安装平台系列高端装备及其设计制造的三大技术难题——腿站立作业易“失稳”、大平台大跨距大倾覆力矩自升易“失控”、高空吊装巨型叶片逾百螺栓精准定位易“失准”,以及焊缝缺陷修复和局部裂纹损伤的激光锻造修复再制造进行了介绍,研制的具有不同规格的系列装备在中国、英国、丹麦、德国等国家的著名海上风电场建设应用情况良好。     

某型柴油机水泵、机油泵间隙调整工装的应用

为了方便某柴油机前端水泵和机油泵齿轮间隙的调整,改变以前传统的调整方法,通过长期在装配现场的观察和了解,设计出某柴油机前端水泵和机油泵齿轮间调整工作,经现场使用验证;该工装安全、小巧轻便精度高,改善了装配的劳动强度和装配质量。     

风机主轴锻件锻后热处理工艺优化

通过对42CrMo4风机主轴结构尺寸、性能要求、材质特点等方面进行分析,对原有锻后热处理工艺进行优化,制定出既能达到锻后热处理效果又经济节能的工艺参数。     

热轧圆钢热顶锻裂纹原因分析

热顶锻合格率是反映热轧圆钢实物质量的一个重要指标。在对国内外热轧圆钢热顶锻质量控制研究成果综述的基础上，对热轧圆钢的热顶锻质量进行了全面的调查、统计和试验研究，归纳了引起热轧圆钢热顶锻裂纹的常见原因，介绍了热顶锻裂纹分析步骤。通过对热顶锻裂纹的形貌和金相组织进行分析，阐述了引起热顶锻裂纹的冶炼因素和轧制因素，并进行了举例说明。     

奥钢联板坯铸机驱动力报警问题的分析及改进

浇铸过程中，驱动力报警会导致紧急停浇甚至滞坯事故发生。为防止事故发生，通常采用降速、强冷等措施，但降速造成成本浪费，强冷又产生裂纹等质量缺陷，两者都难以满足生产需要。通过对铸机的各项参数对比分析，找到影响驱动力报警的主要原因为辊缝异常，轻压下模型参数、冷却工艺设置不合理等，通过调整二冷工艺、优化模型参数、加强轻压下区域扇形段辊缝维护，可以达到明显降低驱动力、消除报警的目的，从而保证连铸生产稳定。     

控轧控冷中碳非调质钢的高周疲劳性能

 采用中碳非调质钢制造的轴类等零件常承受交变载荷，因而对钢材疲劳性能具有高的要求。为了评估控轧控冷工艺生产的非调质钢棒材的疲劳性能，利用旋转弯曲疲劳试验机研究了一种常用的钒微合金化中碳非调质钢38MnVS及对比钢38MnS的高周疲劳性能。结果表明，与38MnS钢相比，38MnVS钢中铁素体体积分数增加，组织明显细化；相分析表明约有54%的钒处于M（C，N）相中，且尺寸小于10 nm的M（C，N）粒子质量分数为32%，这些细小粒子的析出强化增量约为116 MPa。38MnVS钢的疲劳极限较38MnS钢提高了62 MPa，提高幅度约为18%；疲劳极限比从38MnS钢的0.43提高到38MnVS钢的0.48。M（C，N）相的析出强化及组织细化是38MnVS钢较38MnS钢具有优异疲劳性能的主要原因，但其疲劳性能仍低于锻态非调质钢。根据试验结果及文献数据，给出了预测铁素体＋珠光体型非调质钢疲劳极限的简便方法。     

Effect of temperature on fast forging process of Mg-Ni samples for fast formation of Mg2Ni for hydrogen storage

Fast-Forging was used as a Severe Plastic Deformation technique to process Mg/Ni fine powder mixtures at a ratio corresponding to the eutectic composition. The samples were processed at different temperature, increased successively from room temperature up to above 500 °C. The one shock forging operation led to a reduction rate comprised between 80 to more than 90% depending of the applied temperature. Interestingly, a threshold temperature was pointed out for which amounts of the binary Mg₂Ni alloy were directly synthesized in increasing proportions when increasing temperature. A maximum amount of Mg₂Ni was synthesized according the nominal proportions at the highest applied temperature. Besides, numerical simulations were developed to consider and integrate to the forging process, the heat arising from the mechanical energy at deformation. Interestingly the total temperature at shock – heat applied to and heat developed in – indicates that the threshold temperature correspond well with the eutectic temperature as reported in the phase diagram. Early hydrogenation cycles suggest that both mechanical defects in brittle Mg and presence of amounts of Mg₂Ni as catalyst should be combined to optimize the hydrogenation characteristics.     

精密磨床转台静压轴承的强健化设计

针对精密磨床转台静压轴承性能仿真数据与其回转精度实测数据不一致的问题，为提高转台静压轴承的设计水平，提出了静压轴承的强健化设计方法。该方法考虑了轴承结构参数在轴承全生命周期内的变化，分析了半径间隙、油腔尺寸、节流比及润滑油黏度在设计、加工、装配和服役4个阶段的变化规律，重点研究了半径间隙在各阶段对轴承性能造成的影响，给出了转台静压轴承的强健化设计流程。通过一个径向轴承的设计实例对该强健化设计方法进行了说明，并将设计结果与传统设计进行了对比。对比的指标是轴承在4个阶段的刚度、承载力和温升，这3个指标对轴承回转精度有直接影响。研究表明：进行强健化设计后，在生命周期内静压轴承的刚度和承载力的变化量为10%~27%，温度的变化量为0.5%~1.6%，较传统设计更能保证转台回转精度的稳定。     

Transfer learning between crop types for semantic segmentation of crops versus weeds in precision agriculture

Agricultural robots rely on semantic segmentation for distinguishing between crops and weeds to perform selective treatments and increase yield and crop health while reducing the amount of chemicals used. Deep‐learning approaches have recently achieved both excellent classification performance and real‐time execution. However, these techniques also rely on a large amount of training data, requiring a substantial labeling effort, both of which are scarce in precision agriculture. Additional design efforts are required to achieve commercially viable performance levels under varying environmental conditions and crop growth stages. In this paper, we explore the role of knowledge transfer between deep‐learning‐based classifiers for different crop types, with the goal of reducing the retraining time and labeling efforts required for a new crop. We examine the classification performance on three datasets with different crop types and containing a variety of weeds and compare the performance and retraining efforts required when using data labeled at pixel level with partially labeled data obtained through a less time‐consuming procedure of annotating the segmentation output. We show that transfer learning between different crop types is possible and reduces training times for up to 80%. Furthermore, we show that even when the data used for retraining are imperfectly annotated, the classification performance is within 2% of that of networks trained with laboriously annotated pixel‐precision data.