Self-tuning controller apparatus and process control system
    1.
    发明授权
    Self-tuning controller apparatus and process control system 失效
    自调整控制器设备和过程控制系统

    公开(公告)号:US5153807A

    公开(公告)日:1992-10-06

    申请号:US714344

    申请日:1991-06-12

    IPC分类号: G05B13/02

    摘要: A self-tuning controller apparatus which comprises: a control response pattern recognition portion for receiving a set-point and a controlled variable of a process and for obtaining three performance indexes from a controlled variable response pattern generated in response to a change in the set-point or a disturbance; a control parameter correction portion for qualitatively evaluating the three performance indexes and for inferring a correction value of a PID control parameter on the basis of the result of evaluation; and a control performance dissatisfaction degree evaluation portion for evaluating the inferred correction value of the PID control parameter in accordance with the dissatisfaction degrees of the two performance indexes for the respective target specifications of the two of the three performance indexes. The control performance dissatisfaction degree evaluation portion acts to make the PID control parameter converge stably. In a process control system including a plurality of vertically distributed control elements each capable of self-tuning its control parameter, the control performance dissatisfaction degree evaluation portion contributes to autonomous functioning of each of the control elements.

    摘要翻译: 一种自调整控制器装置,包括:控制响应模式识别部分,用于接收过程的设定点和受控变量,并且从响应于所述设定点的变化产生的受控变量响应模式获得三个性能指标, 点或扰动; 控制参数校正部分,用于基于评估结果定性评估三个性能指标并推断PID控制参数的校正值; 以及控制性能不满足度评价部,其根据所述三个性能指标中的两个的各个目标规格的两个性能指标的不满足度来评价PID控制参数的推定校正值。 控制性能不满意度评估部分使PID控制参数稳定收敛。 在包括能够自调整其控制参数的多个垂直分布的控制元件的过程控制系统中,控制性能不满意度评估部分有助于每个控制元件的自主功能。

    Process control method and system for performing control of a controlled
system by use of a neural network
    2.
    发明授权
    Process control method and system for performing control of a controlled system by use of a neural network 失效
    用于通过使用神经网络来控制受控系统的过程控制方法和系统

    公开(公告)号:US5311421A

    公开(公告)日:1994-05-10

    申请号:US625096

    申请日:1990-12-10

    IPC分类号: G05B13/02 G06F15/18

    CPC分类号: G05B13/0285 Y10S706/906

    摘要: A method for controlling a controlled system by a controller such that a controlled variable can be brought into conformity with a desired value. With respect to at least one of input/output variables for a combined controlling-controlled system, which includes in combination the controller and the controlled system, and input/output variables for the controlled system, information containing its characteristics is taken out from the combined controlling-controlled system. The information with the characteristics contained therein is inputted to a neural network which has been caused beforehand to learn a correlation between the information containing the characteristics and control parameters. From the neural network, one or more of the control parameters, said one or more control parameters corresponding to a corresponding number of inputs to the neural network, are outputted to the controller.

    摘要翻译: 一种用于通过控制器控制受控系统的方法,使得受控变量可以与期望值一致。 关于组合的控制控制系统的输入/输出变量中的至少一个,其包括控制器和受控系统的组合以及受控系统的输入/输出变量,从组合中取出包含其特性的信息 控制系统。 其中包含其特征的信息被输入到预先引起的神经网络,以了解包含特征的信息和控制参数之间的相关性。 从神经网络,控制器输出一个或多个控制参数,所述一个或多个控制参数对应于对神经网络的相应数量的输入。