会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 6. 发明申请
    • Adaptive command filtering for servomechanism control systems
    • 伺服机构控制系统的自适应命令过滤
    • US20050285558A1
    • 2005-12-29
    • US11129059
    • 2005-05-12
    • David WattMehmet AlpayMark UnrathJohn WenBen Potsaid
    • David WattMehmet AlpayMark UnrathJohn WenBen Potsaid
    • G05B13/04G05D23/275
    • G05B13/041
    • Preferred embodiments of the invention implement techniques for modifying the command trajectory, the architecture of a servomechanism control system, or both, to reduce the servo error during and/or after the command trajectory. An iterative refinement procedure generates for use by the servomechanism control system a corrective input, du, which significantly reduces the error between the desired and actual servomechanism control system outputs. In one embodiment, a uniquely identified plant model is employed in the iterative refinement procedure to compute an approximate gradient that improves the performance and reliability of the refinement procedure. In another embodiment, the actual plant response is used in place of the identified model in the iterative refinement procedure. This is accomplished by time-reversing the stored error signal from a training run, before applying it to the plant to generate an update to the corrective input signal du.
    • 本发明的优选实施例实现了用于修改命令轨迹,伺服机构控制系统的结构或两者的技术,以减少在命令轨迹期间和/或之后的伺服误差。 对伺服机构控制系统产生的迭代精制过程可用于校正输入du,这显着地减少了期望的和实际的伺服机构控制系统输出之间的误差。 在一个实施例中,在迭代细化过程中采用唯一识别的植物模型来计算提高细化过程的性能和可靠性的近似梯度。 在另一个实施例中,在迭代细化过程中使用实际植物响应来代替所识别的模型。 这是通过将训练运行中存储的误差信号时间反转,然后将其应用到工厂来产生对纠正输入信号du的更新来实现的。
    • 8. 发明申请
    • Image quality via multi-wavelength light
    • 图像质量通过多波长光
    • US20070253033A1
    • 2007-11-01
    • US11414678
    • 2006-04-28
    • Brian JohansenMehmet Alpay
    • Brian JohansenMehmet Alpay
    • H04N1/40
    • G01N21/8851G01N21/9501G06K9/2018G06K9/2027G06K2209/19G06T5/50
    • A method and apparatus to improve image quality in images captured via monochromatic cameras using multi-wavelength lighting. A contrast optimization algorithm determines which particular wavelength among those available is most suitable to maximize contrast. The quality of the image can be further improved through active noise cancellation by determining the lighting schemes that provide maximum and minimum contrast between a target and a background. The elimination of image texture data (i.e., noise) is then accomplished through pixel-by-pixel division of the maximum by the minimum contrast image. Alternatively, images obtained using at least two wavelengths can be algebraically combined for noise reduction. The resulting composite image can be fed into any known target identification algorithm.
    • 一种改善通过使用多波长照明的单色相机拍摄的图像中的图像质量的方法和装置。 对比度优化算法确定可用的那些特定波长最适合于最大化对比度。 通过确定在目标和背景之间提供最大和最小对比度的照明方案,可以通过主动噪声消除来进一步改善图像的质量。 然后通过最小对比度图像的逐像素划分来完成消除图像纹理数据(即,噪声)。 或者,使用至少两个波长获得的图像可以被代数组合用于降噪。 所得到的合成图像可以被馈送到任何已知的目标识别算法中。
    • 9. 发明授权
    • Adaptive command filtering for servomechanism control systems
    • 伺服机构控制系统的自适应命令过滤
    • US07345448B2
    • 2008-03-18
    • US11129059
    • 2005-05-12
    • David WattMehmet AlpayMark UnrathJohn WenBen Potsaid
    • David WattMehmet AlpayMark UnrathJohn WenBen Potsaid
    • G05B13/02
    • G05B13/041
    • Preferred embodiments of the invention implement techniques for modifying the command trajectory, the architecture of a servomechanism control system, or both, to reduce the servo error during and/or after the command trajectory. An iterative refinement procedure generates for use by the servomechanism control system a corrective input, du, which significantly reduces the error between the desired and actual servomechanism control system outputs. In one embodiment, a uniquely identified plant model is employed in the iterative refinement procedure to compute an approximate gradient that improves the performance and reliability of the refinement procedure. In another embodiment, the actual plant response is used in place of the identified model in the iterative refinement procedure. This is accomplished by time-reversing the stored error signal from a training run, before applying it to the plant to generate an update to the corrective input signal du.
    • 本发明的优选实施例实现了用于修改命令轨迹,伺服机构控制系统的结构或两者的技术,以减少在命令轨迹期间和/或之后的伺服误差。 对伺服机构控制系统产生的迭代精制过程可用于校正输入du,这显着地减少了期望的和实际的伺服机构控制系统输出之间的误差。 在一个实施例中,在迭代细化过程中采用唯一识别的植物模型来计算提高细化过程的性能和可靠性的近似梯度。 在另一个实施例中,在迭代细化过程中使用实际植物响应来代替所识别的模型。 这是通过将训练运行中存储的误差信号时间反转,然后将其应用到工厂来产生对纠正输入信号du的更新来实现的。