-
1.发明授权公开(公告)号：US06757570B1
公开(公告)日：2004-06-29
申请号：US09585105
申请日：2000-05-31
IPC分类号： G05B1302
CPC分类号： G05B13/027 , G05D1/0825
摘要： A process and neural network architecture for on-line adjustment of the weights of the neural network in a manner that corrects errors made by a nonlinear controller designed based on a model for the dynamics of a process under control. A computer system is provided for controlling the dynamic output response signal of a nonlinear physical process, where the physical process is represented by a fixed model of the process. The computer system includes a controlled device for responding to the output response signal of the system. The computer system also includes a linear controller for providing a pseudo control signal that is based on the fixed model for the process and provides a second controller, connected to the linear controller, for receiving the pseudo control signal and for providing a modified pseudo control signal to correct for the errors made in modeling the nonlinearities in the process. A response network is also included as part of the computer system. The response network receives the modified pseudo control signal and provides the output response signal to the controlled device. The second controller preferably is a neural network. The computer system may include a plurality of neural networks with each neural network designated to control a selected variable or degree of freedom within the system.
摘要翻译： 一种过程和神经网络架构，用于以校正由基于控制的过程的动力学的模型设计的非线性控制器所做的错误的方式在线调整神经网络的权重。 提供了一种用于控制非线性物理过程的动态输出响应信号的计算机系统，其中物理过程由该过程的固定模型表示。 计算机系统包括用于响应系统的输出响应信号的受控设备。 计算机系统还包括线性控制器，用于提供基于该过程的固定模型的伪控制信号，并提供连接到线性控制器的第二控制器，用于接收伪控制信号并提供经修改的伪控制信号 以纠正在过程中对非线性建模的错误。 响应网络也作为计算机系统的一部分。 响应网络接收修改后的伪控制信号，并向受控设备提供输出响应信号。 第二控制器优选地是神经网络。 计算机系统可以包括多个神经网络，每个神经网络被指定用于控制系统内的选定变量或自由度。
-
2.发明授权
公开(公告)号：US6092919A
公开(公告)日：2000-07-25
申请号：US510055
申请日：1995-08-01
申请人： Anthony J. Calise , Byoung-Soo Kim
发明人： Anthony J. Calise , Byoung-Soo Kim
IPC分类号： G05B13/02
CPC分类号： G05B13/027 , G05D1/0825
摘要： A process and neural network architecture for on-line adjustment of the weights of the neural network in a manner that corrects errors made by a nonlinear controller designed based on a model for the dynamics of a process under control. A computer system is provided for controlling the dynamic output response signal of a nonlinear physical process, where the physical process is represented by a fixed model of the process. The computer system includes a controlled device for responding to the output response signal of the system. The computer system also includes a linear controller for providing a pseudo control signal that is based on the fixed model for the process and provides a second controller, connected to the linear controller, for receiving the pseudo control signal and for providing a modified pseudo control signal to correct for the errors made in modeling the nonlinearities in the process. A response network is also included as part of the computer system. The response network receives the modified pseudo control signal and provides the output response signal to the controlled device. The second controller preferably is a neural network. The computer system may include a plurality of neural networks with each neural network designated to control a selected variable or degree of freedom within the system.
摘要翻译： 一种过程和神经网络架构，用于以校正由基于控制的过程的动力学的模型设计的非线性控制器所做的错误的方式在线调整神经网络的权重。 提供了一种用于控制非线性物理过程的动态输出响应信号的计算机系统，其中物理过程由该过程的固定模型表示。 计算机系统包括用于响应系统的输出响应信号的受控设备。 计算机系统还包括线性控制器，用于提供基于该过程的固定模型的伪控制信号，并提供连接到线性控制器的第二控制器，用于接收伪控制信号并提供经修改的伪控制信号 以纠正在过程中对非线性建模的错误。 响应网络也作为计算机系统的一部分。 响应网络接收修改后的伪控制信号，并向受控设备提供输出响应信号。 第二控制器优选地是神经网络。 计算机系统可以包括多个神经网络，每个神经网络被指定用于控制系统内的选定变量或自由度。
-
3.发明授权公开(公告)号：US07415311B2
公开(公告)日：2008-08-19
申请号：US11620032
申请日：2007-01-04
CPC分类号： G05B13/027 , G05D1/0825
摘要： A computer system for controlling a nonlinear physical process. The computer system comprises a linear controller and a neural network. The linear controller receives a command signal for control of the nonlinear physical process and a measured output signal from the output of the nonlinear physical process. The linear controller generates a control signal based on the command signal, a measured output signal, and a fixed linear model for the process. The neural network receives the control signal from the linear controller and the measured output signal from the output of the nonlinear physical process. The neural network uses the measured output signal to modify the connection weights of the neural network. The neural network also generates a modified control signal supplied to the linear controller to iterate a fixed point solution for the modified control signal used to control the nonlinear physical process.
摘要翻译： 一种用于控制非线性物理过程的计算机系统。 计算机系统包括线性控制器和神经网络。 线性控制器接收用于控制非线性物理过程的命令信号和来自非线性物理过程的输出的测量输出信号。 线性控制器基于命令信号，测量输出信号和用于该过程的固定线性模型产生控制信号。 神经网络接收来自线性控制器的控制信号和来自非线性物理过程的输出的测量输出信号。 神经网络使用测量的输出信号来修改神经网络的连接权重。 神经网络还生成提供给线性控制器的修改的控制信号，以迭代用于控制非线性物理过程的修改的控制信号的固定点解。
-
4.发明授权公开(公告)号：US07177710B2
公开(公告)日：2007-02-13
申请号：US11147671
申请日：2005-06-07
申请人： Anthony J. Calise , Byoung-Soo Kim
发明人： Anthony J. Calise , Byoung-Soo Kim
CPC分类号： G05B13/027 , G05D1/0825
摘要： A computer system for controlling a nonlinear physical process. The computer system comprises a linear controller and a neural network. The linear controller receives a command signal for control of the nonlinear physical process and a measured output signal from the output of the nonlinear physical process. The linear controller generates a control signal based on the command signal, a measured output signal, and a fixed linear model for the process. The neural network receives the control signal from the linear controller and the measured output signal from the output of the nonlinear physical process. The neural network uses the measured output signal to modify the connection weights of the neural network. The neural network also generates a modified control signal supplied to the linear controller to iterate a fixed point solution for the modified control signal used to control the nonlinear physical process.
摘要翻译： 一种用于控制非线性物理过程的计算机系统。 计算机系统包括线性控制器和神经网络。 线性控制器接收用于控制非线性物理过程的命令信号和来自非线性物理过程的输出的测量输出信号。 线性控制器基于命令信号，测量输出信号和用于该过程的固定线性模型产生控制信号。 神经网络接收来自线性控制器的控制信号和来自非线性物理过程的输出的测量输出信号。 神经网络使用测量的输出信号来修改神经网络的连接权重。 神经网络还生成提供给线性控制器的修改的控制信号，以迭代用于控制非线性物理过程的修改的控制信号的固定点解。
-
公开(公告)号：US20050024148A1
公开(公告)日：2005-02-03
申请号：US10899470
申请日：2004-07-26
申请人： Tae-Jin Kim , Seung-Wook Lee , Byoung-Soo Kim , Yong-Woo Kim , Young-Woong Kim , Jin-Ho Shin
发明人： Tae-Jin Kim , Seung-Wook Lee , Byoung-Soo Kim , Yong-Woo Kim , Young-Woong Kim , Jin-Ho Shin
摘要： A bias circuit for a smart power amplifier includes a high power mode bias circuit and a low power mode bias circuit, and operates only one of the bias circuits selectively using a switching circuit according to an input signal. Therefore, the bias circuit of high power mode and the bias circuit of the low power mode are divided and can be optimized according to characteristics of the power. Accordingly, a gain difference with respect to each power can be minimized and the low power mode can be controlled with a small amount of current in a state of initial current with a low power and in a middle power, such that an efficiency of the power amplifier can be improved at low power.
摘要翻译： 用于智能功率放大器的偏置电路包括高功率模式偏置电路和低功率模式偏置电路，并且仅使用根据输入信号的开关电路来选择性地操作一个偏置电路。 因此，高功率模式的偏置电路和低功耗模式的偏置电路被划分，可以根据电源的特性进行优化。 因此，可以将每个功率的增益差最小化，并且可以在低功率和中功率的初始电流的状态下以少量的电流来控制低功率模式，使得功率的效率 放大器可以在低功耗下进行改进。
-
6.发明申请公开(公告)号：US20070260565A1
公开(公告)日：2007-11-08
申请号：US11620032
申请日：2007-01-04
申请人： Anthony Calise , Byoung-Soo Kim , J. Corban
发明人： Anthony Calise , Byoung-Soo Kim , J. Corban
IPC分类号： G06N3/02
CPC分类号： G05B13/027 , G05D1/0825
摘要： A computer system for controlling a nonlinear physical process. The computer system comprises a linear controller and a neural network. The linear controller receives a command signal for control of the nonlinear physical process and a measured output signal from the output of the nonlinear physical process. The linear controller generates a control signal based on the command signal, a measured output signal, and a fixed linear model for the process. The neural network receives the control signal from the linear controller and the measured output signal from the output of the nonlinear physical process. The neural network uses the measured output signal to modify the connection weights of the neural network. The neural network also generates a modified control signal supplied to the linear controller to iterate a fixed point solution for the modified control signal used to control the nonlinear physical process.
摘要翻译： 一种用于控制非线性物理过程的计算机系统。 计算机系统包括线性控制器和神经网络。 线性控制器接收用于控制非线性物理过程的命令信号和来自非线性物理过程的输出的测量输出信号。 线性控制器基于命令信号，测量输出信号和用于该过程的固定线性模型产生控制信号。 神经网络接收来自线性控制器的控制信号和来自非线性物理过程的输出的测量输出信号。 神经网络使用测量的输出信号来修改神经网络的连接权重。 神经网络还生成提供给线性控制器的修改的控制信号，以迭代用于控制非线性物理过程的修改的控制信号的固定点解。
-
7.发明申请GENERAL-PURPOSE PERIPHERAL INTERFACE, A METHOD OF INTERFACING, AND AN APPARATUS HAVING THE SAME FOR CONTROLLING A ROBOT 审中-公开通用外围接口，接口方法，以及具有控制机器人的装置公开(公告)号：US20150081094A1
公开(公告)日：2015-03-19
申请号：US14360300
申请日：2012-05-21
申请人： Byoung-Soo Kim , In Yong Ha
发明人： Byoung-Soo Kim , In Yong Ha
IPC分类号： B25J9/16
CPC分类号： B25J9/16 , B25J13/00 , G05B19/414 , G05B2219/21008 , G05B2219/21085 , G05B2219/25296 , G05B2219/32141
摘要： A general-purpose peripheral interface according to an exemplary embodiment of the present invention includes a pair of complementary connectors including at least one input terminal, at least one output terminal, and at least one power supply terminal and ground terminal, wherein when a connector of a peripheral device is combined to a connector of a control device, an identification voltage in a voltage range varying according to a type of the peripheral device is shown in the input terminal. Here, the voltage ranges may be set not to overlap each other when the types of the peripheral devices are different. The type of the peripheral device may be one of an input type, an input-output mixed type, and an output type.
摘要翻译： 根据本发明的示例性实施例的通用外围设备接口包括一对互补连接器，其包括至少一个输入端子，至少一个输出端子以及至少一个电源端子和接地端子，其中当连接器 将外围设备组合到控制设备的连接器，在输入端子中示出了根据外围设备的类型而变化的电压范围内的识别电压。 这里，当外围设备的类型不同时，可以将电压范围设定为不相互重叠。 外围设备的类型可以是输入类型，输入输出混合类型和输出类型之一。
-
公开(公告)号：US07129786B2
公开(公告)日：2006-10-31
申请号：US10899470
申请日：2004-07-26
申请人： Tae-Jin Kim , Seung-Wook Lee , Byoung-Soo Kim , Yong-Woo Kim , Young-Woong Kim , Jin-Ho Shin
发明人： Tae-Jin Kim , Seung-Wook Lee , Byoung-Soo Kim , Yong-Woo Kim , Young-Woong Kim , Jin-Ho Shin
IPC分类号： H03F3/04
摘要： A bias circuit for a smart power amplifier includes a high power mode bias circuit and a low power mode bias circuit, and operates only one of the bias circuits selectively using a switching circuit according to an input signal. Therefore, the bias circuit of high power mode and the bias circuit of the low power mode are divided and can be optimized according to characteristics of the power. Accordingly, a gain difference with respect to each power can be minimized and the low power mode can be controlled with a small amount of current in a state of initial current with a low power and in a middle power, such that an efficiency of the power amplifier can be improved at low power.
摘要翻译： 用于智能功率放大器的偏置电路包括高功率模式偏置电路和低功率模式偏置电路，并且仅使用根据输入信号的开关电路来选择性地操作一个偏置电路。 因此，高功率模式的偏置电路和低功耗模式的偏置电路被划分，并可以根据电源的特性进行优化。 因此，可以将每个功率的增益差最小化，并且可以在低功率和中功率的初始电流的状态下以少量的电流来控制低功率模式，使得功率的效率 放大器可以在低功耗下进行改进。
-
公开(公告)号：US20080168633A1
公开(公告)日：2008-07-17
申请号：US12007611
申请日：2008-01-14
申请人： Byoung-Soo Kim , Jung-Ho Lee
发明人： Byoung-Soo Kim , Jung-Ho Lee
CPC分类号： F16B5/0642 , F16B5/0657 , Y10T24/45 , Y10T403/75
摘要： An elastic fastener has developed to be assembled and disassembled easily, even without the use of a separate tool, that can be firmly and repeatedly coupled, and an actuator module using the same. The elastic fastener includes a hollow socket adapted to be elastically inserted into insertion holes formed on joint members, and a fixing pin coupled to a hollow portion of the hollow socket. The actuator module includes a housing including a first lateral plate having at least one insertion hole for inserting an elastic fastener, a second lateral plate positioned to face the first lateral plate and provided with at least one insertion hole of an identical shape as the insertion hole of the first lateral plate, and two lateral surfaces positioned between both ends of the first and second lateral plates while facing each other; a first connection member coupled to a driving shaft of an actuator contained in the housing via the first lateral plate, the first connection member having at least one insertion hole of an identical shape as the insertion holes of the first and second lateral plates, the first connection member having a flat plate shape; and an elastic fastener including a hollow socket adapted to be elastically inserted into the insertion hole formed in the first connection member and a fixing pin coupled to the hollow portion of the hollow socket.
摘要翻译： 弹性紧固件已经开发成易于组装和拆卸，即使不使用可以牢固且重复地联接的单独的工具，以及使用该紧固件的致动器模块。 弹性紧固件包括适于被弹性地插入到形成在接合构件上的插入孔中的中空插座，以及联接到中空插座的中空部分的固定销。 致动器模块包括壳体，该壳体包括具有用于插入弹性紧固件的至少一个插入孔的第一侧板，与第一侧板相对设置的第二侧板，并且设置有与插入孔相同形状的至少一个插入孔 并且两个侧表面位于第一和第二侧板的两端之间，同时彼此面对; 第一连接构件，其经由第一侧板联接到容纳在壳体中的致动器的驱动轴，第一连接构件具有至少一个与第一和第二侧板的插入孔相同形状的插入孔，第一连接构件 具有平板形状的连接构件; 以及弹性紧固件，其包括适于被弹性地插入形成在第一连接构件中的插入孔中的中空插座和连接到中空插座的中空部分的固定销。
-
10.发明申请公开(公告)号：US20070010902A1
公开(公告)日：2007-01-11
申请号：US11147671
申请日：2005-06-07
申请人： Anthony Calise , Byoung-Soo Kim
发明人： Anthony Calise , Byoung-Soo Kim
IPC分类号： G05B13/02
CPC分类号： G05B13/027 , G05D1/0825
摘要： A computer system for controlling a nonlinear physical process. The computer system comprises a linear controller and a neural network. The linear controller receives a command signal for control of the nonlinear physical process and a measured output signal from the output of the nonlinear physical process. The linear controller generates a control signal based on the command signal, a measured output signal, and a fixed linear model for the process. The neural network receives the control signal from the linear controller and the measured output signal from the output of the nonlinear physical process. The neural network uses the measured output signal to modify the connection weights of the neural network. The neural network also generates a modified control signal supplied to the linear controller to iterate a fixed point solution for the modified control signal used to control the nonlinear physical process.
摘要翻译： 一种用于控制非线性物理过程的计算机系统。 计算机系统包括线性控制器和神经网络。 线性控制器接收用于控制非线性物理过程的命令信号和来自非线性物理过程的输出的测量输出信号。 线性控制器基于命令信号，测量输出信号和用于该过程的固定线性模型产生控制信号。 神经网络接收来自线性控制器的控制信号和来自非线性物理过程的输出的测量输出信号。 神经网络使用测量的输出信号来修改神经网络的连接权重。 神经网络还生成提供给线性控制器的修改的控制信号，以迭代用于控制非线性物理过程的修改的控制信号的固定点解。
-
-
-
-
-
-
-
-
-
搜索结果
11 条记录 (耗时 0.017 秒)
