公开(公告)号：US06577960B1

公开(公告)日：2003-06-10

申请号：US09615455

申请日：2000-07-13

申请人： Luis C. Rabelo ,  Mark Walker ,  Radoslaw R. Zakrewski

发明人： Luis C. Rabelo ,  Mark Walker ,  Radoslaw R. Zakrewski

IPC分类号： G01F1700

CPC分类号： G01F23/2962 ,  G01F23/0069 ,  G01F23/0076 ,  G01F23/266

摘要： Liquid gauging apparatus using a time delay neural network for determining a quantity of liquid in a container that is not directly measurable by sensors is disclosed. The apparatus comprises a plurality of sensors and a processor. Each of the sensors are capable of measuring a respective parameter of the liquid and for producing a time varying sensor output signal representative of the respective parameter measured thereby. The processor is programmed to process the sensor output signals by a time delay neural network algorithm to determine a current quantity of the liquid in the container based on current and past parameter measurements of the sensor output signals. Also disclosed is a method of training a time delay neural network algorithm for computing a quantity of liquid in a container from current and past liquid parameter sensor measurements. The method comprises the steps of: establishing a dynamic model of liquid behavior in the container and parameter measurements of the liquid behavior sensed by a plurality of sensors; deriving from the dynamic model training data sets for a plurality of liquid quantity values, each data set comprising current and past liquid parameter sensor measurement values corresponding to a liquid quantity value of the plurality, and the corresponding liquid quantity value; and training the time delay neural network algorithm with the derived training data sets.

摘要翻译： 公开了一种使用时间延迟神经网络来确定容器中不能被传感器直接测量的液体量的液体计量装置。 该装置包括多个传感器和处理器。 每个传感器能够测量液体的相应参数，并且用于产生表示由此测量的相应参数的时变传感器输出信号。 处理器被编程为通过时间延迟神经网络算法处理传感器输出信号，以基于传感器输出信号的当前和过去的参数测量来确定容器中液体的当前量。 还公开了一种训练用于从当前和过去的液体参数传感器测量计算容器中的液体量的时间延迟神经网络算法的方法。 该方法包括以下步骤：建立容器中液体行为的动态模型和由多个传感器感测的液体行为的参数测量; 从多个液体量值的动态模型训练数据集中得出的每个数据集包括与多个液体量值对应的当前和过去的液体参数传感器测量值和相应的液体量值; 并用导出的训练数据集训练时间延迟神经网络算法。

公开(公告)号：US06502042B1

公开(公告)日：2002-12-31

申请号：US09697674

申请日：2000-10-26

申请人： Bradley F. Eid ,  Radoslaw R. Zakrewski ,  Mark G. Walker

发明人： Bradley F. Eid ,  Radoslaw R. Zakrewski ,  Mark G. Walker

IPC分类号： G06E1900

CPC分类号： G01F23/268 ,  G01F23/0069

摘要： A fault tolerant liquid measurement system includes a plurality of sensors for measuring parameters of a liquid in a container; each sensor generating a measurement signal representative of the liquid parameter measured thereby. The sensors are grouped into a number of sets, each set including some sensors of another set. The measurement signals of each set of sensors are processed in a processor to determine for each set of sensors a first estimate signal representative of a likelihood of measurement signal validity for the measurement signals of the corresponding set, and a second estimate signal representative of liquid quantity in the container based on the measurement signals of the corresponding set. The processor further determines a third estimate signal of liquid quantity in the container based on a function of the first and second estimate signals.

摘要翻译： 容错液体测量系统包括用于测量容器中液体的参数的多个传感器; 每个传感器产生表示由此测量的液体参数的测量信号。 传感器被分组成多个组，每组包括另一组的一些传感器。 每个传感器组的测量信号在处理器中进行处理，以确定每组传感器的第一估计信号，其表示相应组的测量信号的测量信号有效性的可能性，以及表示液体量的第二估计信号 在容器中基于相应组的测量信号。 处理器还基于第一和第二估计信号的函数进一步确定容器中液体量的第三估计信号。