分类： 机械工程 >> 机械制造自动化 提交时间： 2024-01-07
摘要： 近年来，随着我国炼化行业与信息技术的深入融合与飞速发展，复杂炼化系统所产生的数据呈现爆炸性增长。报警系统是一类用于向操作者传递设备异常状态信息的监控系统；一旦设计不合理，设备在异常状态下可能会产生大量的过程报警甚至报警饱和的现象，严重影响操作者的信息处理能力，从而增加各种工业事故的发生概率。报警信息能够对复杂炼化过程给予正向的指导，因此如何从海量的报警日志中挖掘有价值的信息非常重要。深度学习是一种能够自动地从数据中学习和提取特征的方法，不需要人工构建复杂而精确的物理和数学模型，已在数据预测和分类领域得到广泛应用和关注。
分类： 机械工程 >> 机械制造自动化 提交时间： 2022-10-21
摘要： With growing interest in Laser Additive Manufacturing (LAM) of High-entropy alloys (HEAs) during most recent years, compositional elements design and process strategies innovation are primary methods to overcome undesirable microstructures and defects. Here we propose a new approach, a novel real-time laser shock modulation of melt pool (LSMMP) to obtain melt pool modifications for yielding HEAs with desired characteristics. LSMMP utilizes a pulsed laser shocking a liquid melt pool caused by a continuous wave laser, enabling non-destructive and real-time modulations for high-performance HEAs. The numerical simulation reveals the convection mechanism of the melt pool in the LSMMP process, and the intervention of the pulsed laser promotes melt pool flow type to convert the Marangoni effect into a multi-convective ring, which accelerates melt pool flow and inhibits columnar crystal growth. Experimental results show the evolution law of the microstructure in the LSMMP process. The microstructure of CrFeCoNi HEAs undergoes a Columnar-Equiaxed Transition (CET), and higher hardness is obtained. Laser shock is demonstrated to be an effective in-situ modulative tool for controlled additive manufacturing.
分类： 机械工程 >> 机械制造自动化 提交时间： 2022-09-26 合作期刊: 《桂林电子科技大学学报》
摘要： 为验证某款燃料电池商用车动力系统选型的合理性,以该款车型动力系统的关键参数为基础,在Matlab仿真平台上搭建包含复合能量源(包含燃料电池和蓄电池包)、电机系统(包含驱动电机和电机控制器)及车辆传动系统(包含主减速器和车轮)的模型。采用基于动态规划算法的全局优化能量管理策略,设定空载、半载和满载3种载重模式,以欧洲典型行驶工况EUDC_LOW 为仿真工况,分析车辆在不同载重模式下的动力经济性。仿真结果显示,在3种载重模式下,车辆配置的复合能量源均能满足车辆在指定行驶工况下的功率要求,但随着车辆载重的增大,蓄电池包终端SOC逐渐偏离初始值,考虑到商用车需要在大载重的模式下工作较长时间,较低的SOC不利于车辆保持最佳的动力性。针对该车型的验证结果表明,在后续的研究和实车验证中,应考虑配置功率更大的车载燃料电池。
分类： 机械工程 >> 机械制造自动化 提交时间： 2022-09-26 合作期刊: 《桂林电子科技大学学报》
摘要： 针对机器人动力学模型复杂、冗余计算导致运算效率低的问题,提出一种程式化建模方法(PMM)。以六自由度斯 坦福机械臂为例,利用该方法建立基于拉格朗日方程的动力学模型,按照正向分析,逆序输出的核心思想,重点分析模型 递推过程;在验证模型正确性的基础上,比较使用PMM和未使用PMM 的常规拉格朗日方程所建立的斯坦福机械臂力学 模型在计算机中的尺寸和运行时间等指标。实验结果表明,相对常规拉格朗日方法,由PMM 所建模型的复杂程度降低 了67.6%,计算效率提高了66.3%;斯坦福机械臂为完整约束系统,将PMM推广到欠驱动非完整约束系统,采用与模型紧 密相关的部分反馈线性化控制算法进行数值仿真和物理样机实验分析,验证了PMM 的可靠性和有效性,为不同类型的机 器人提供了一种效率高、通用性强的动力学建模方法。
分类： 机械工程 >> 机械制造自动化 提交时间： 2022-05-31
摘要： With growing interest in Laser Additive Manufacturing (LAM) of High-entropy alloys (HEAs) during most recent years, the design of compositional elements and process strategies are primary methods to overcome undesirable microstructures and defects. Here we propose a new approach, a novel real-time Laser Shocking of Melt Pool (LSMP), to obtain melt pool modifications for yielding HEAs with desired characteristics. LSMP utilizes a pulsed laser shocking a liquid melt pool caused by a continuous wave laser, enabling non-destructive and real-time modulations for high-performance HEAs. The numerical simulation reveals the convection mechanism of the melt pool in the LSMP process, and the intervention of the pulsed laser promotes melt pool flow type to convert the Marangoni effect into a multi-convective ring, which accelerates melt pool flow and inhibits columnar crystal growth. Experimental results show the evolution law of the microstructure in the LSMP process. The microstructure of CrFeCoNi HEAs undergoes a Columnar-Equiaxed Transition (CET), and higher hardness is obtained. Laser shock is demonstrated to be an effective in-situ modulative tool for controlled additive manufacturing.
分类： 机械工程 >> 机械制造自动化 提交时间： 2018-03-16
摘要： 根据移栽蔬菜田间锄草作业工况和要求，基于视觉伺服控制技术，设计了电驱锄草机器人系统。该系统以中小功率拖拉机为配套动力，由伺服电动机驱动月牙形锄草刀护苗锄草和对行，减少了能耗与污染物排放，提高了系统伺服特性。机器视觉系统实时采集田间图像并处理，对作物进行识别与定位。控制器结合视觉系统获取的刀苗距、锄草机器人前进速度、锄刀相位角度及机器人横向偏差信息，利用智能伺服驱动器精确控制锄草刀避苗和对行。试验表明，在前进速度不高于1.5km/h、作物株距不小于0.35m工况下，伤苗率小于10%，田间杂草锄净率约为90%。
分类： 机械工程 >> 机械制造自动化 提交时间： 2018-03-16
摘要： A machine-vision-based method of locating crops is described in this research. This method was used to provide real-time positional information of crop plants for a mechanical intra-row weeding robot. Within the normalized red, green, and blue chromatic coordinates (rgb), a modified excess green feature (g-r>T & g-b>T) was used to segment plant material from back ground in color images. The threshold T was automatically selected by the maximum variance (OTSU) algorithm to cope with variable natural light. Taking into account the geometry of the camera arrangement and the crop row spacing, the target regions covering the crop rows were defined based on a pinhole camera model. According to the statistical variation in the pixel histogram in each target region, locations of the crop plants were initially estimated. To obtain the accurate locations of crops, median filtering was conducted locally in the bounding boxes of the crops close to the bottom of the images. For the lateral guidance of the robot, a novel method of calculating lateral offset was proposed based on a simplified match between a template and the detected crops. Field experiments were conducted under three different illumination conditions. The results showed that the accurate identification rates on lettuce, cauliflower and maize were all above 95%. The positional error as within ±15 mm, and the average processing time for a 640×480 image was 31 ms. The method was adequate to meet the technical requirement of the weeding robot, and laid a foundation for robotic weeding in commercial production system.
点击量
待评议
点击量
下载量
评论
通过
