20MnCr5圆棒锯切困难原因分析

某厂在锯切20MnCr5圆棒过程中锯条容易断裂，采用光学显微镜(OM)和扫描电子显微镜(SEM)等观察分析手段，对锯条容易断裂的原因进行分析。分析结果表明：锯条断裂的原因为加工20MnCr5过程中粘刀崩齿。针对此类加工缺陷，提出了相应的改进措施。     

Recursive algorithm for modeling non-linear etching rates in reactive plasma jet based optical surface machining of borosilicate crown glass

Application-specific optical glass properties are achieved by utilizing complex material compositions. This can be problematic in reactive plasma-assisted deterministic surface processing since a non-volatile surface layer may form depending on the glass composition, which affects the etch rate and thereby the local etching depth. In this investigation, a model algorithm is proposed to tackle some restrictions in applying fluorine-based plasma jet as etching tool utilized for freeform surface machining of optics made of complex glass composition, like borosilicate crown glass (e.g., N-BK7®). In this regard, firstly an analytical model is proposed for estimating the depth-dependent etch rate function. Subsequently, a recursive simulation algorithm is introduced for convolving the derived depth-dependent etch rate function with the given dwell time matrix to simulate a deterministic freeform generation process. By the proposed simulation algorithm, the impeding influence of the residual layer on the reduction of etching depth is computed prior to a real experiment in order to scale the local dwell time to ensure the targeted local removal. Finally, the simulated freeform shape is compared with the corresponding result of an etching experiment to validate the feasibility of the proposed approach.     

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。     

Wire electrical discharge machinable SiC with GNPs and GO as the electrically conducting filler

SiC based composites filled with graphene nano-platelets (GNPs) or graphene oxide (GO) prepared by rapid hot-pressing exhibit sufficient electrical conductivity for their machinability by wire electro-discharge machining (WEDM). Composites microstructure anisotropy caused by graphene alignment as a consequence of rapid hot pressing was confirmed by measuring of electrical conductivity and thermal diffusivity. Electrical conductivity increased significantly with increased weight fraction of graphene in both measured directions. Highest value of 2031 S/m was obtained for composites with 15 wt. % of GNPs in parallel direction and only 1246 S/m in perpendicular direction to aligned GNPs. Thermal diffusivity is 63.3 mm²/s in parallel and only 23.3 mm²/s in perpendicular direction. The increase of the electrical conductivity has resulted in successful WEDM. The MRR was almost doubled when the filler concentration increased from 5 wt. % GNPs/GO to 15 wt. % GNPs. At the same time, the surface roughness decreased.     

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。     

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。     

基于修正等速运动规律的自由曲面多轴加工刀轴序列优化方法

针对自由曲面多轴加工中起始位置处刀具相对工件速度、加速度不为零导致的一定程度刚性冲击现象,提出了一种基于修正等速运动规律的刀轴序列优化方法,通过控制工件坐标系中决定刀具姿态的两个约束角,使之变化遵循修正等速运动规律,获得了切削行上平稳变化的刀轴序列,避免了由于起始位置处刀具相对工件速度、加速度不为零导致刀具不能精准到达后续加工位置的现象。算例分析表明,该方法能产生平稳且光滑的刀轴序列,可一定程度改善机床运动性能,提高加工表面质量。     

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.     

铣削加工每齿进给量的决定因素研究及验证

研究了面铣刀的主偏角对切屑厚度和每齿进给量的影响,铣削中每齿进给量的决定因素,切削宽度与刀具直径的比值对切屑厚度的影响等问题进行理论分析,同时结合变速箱壳体铣削加工过程进行验证,解决了合理选择铣刀及切削参数以提升加工效率的问题。