专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US06278962B1 Hybrid linear-neural network process control 失效
公开(公告)号：US06278962B1
公开(公告)日：2001-08-21
申请号：US09165854
申请日：1998-10-02
申请人： Casimir C. Klimasauskas , John P. Guiver
发明人： Casimir C. Klimasauskas , John P. Guiver
IPC分类号： G06F760
CPC分类号： G05B19/042 , G05B13/027 , G05B13/0275
摘要： A hybrid analyzer having a data derived primary analyzer and an error correction analyzer connected in parallel is disclosed. The primary analyzer, preferably a data derived linear model such as a partial least squares model, is trained using training data to generate major predictions of defined output variables. The error correction analyzer, preferably a neural network model is trained to capture the residuals between the primary analyzer outputs and the target process variables. The residuals generated by the error correction analyzer is summed with the output of the primary analyzer to compensate for the error residuals of the primary analyzer to arrive at a more accurate overall model of the target process. Additionally, an adaptive filter can be applied to the output of the primary analyzer to further capture the process dynamics. The data derived hybrid analyzer provides a readily adaptable framework to build the process model without requiring up-front knowledge. Additionally, the primary analyzer, which incorporates the PLS model, is well accepted by process control engineers. Further, the hybrid analyzer also addresses the reliability of the process model output over the operating range since the primary analyzer can extrapolate data in a predictable way beyond the data used to train the model. Together, the primary and the error correction analyzers provide a more accurate hybrid process analyzer which mitigates the disadvantages, and enhances the advantages, of each modeling methodology when used alone.

2. 发明授权

US6110214A Analyzer for modeling and optimizing maintenance operations 失效
标题翻译：用于建模和优化维护操作的分析仪
公开(公告)号：US6110214A
公开(公告)日：2000-08-29
申请号：US702148
申请日：1996-08-23
申请人： Casimir C. Klimasauskas
发明人： Casimir C. Klimasauskas
IPC分类号： G05B13/02 , G05B19/042 , G06F19/00
CPC分类号： G05B13/027 , G05B13/0275 , G05B19/042
摘要： A first model or first analyzer having a series of filters is provided to represent time-varying effects of maintenance events. The first model or analyzer further enhances the selection of derived variables which are used as inputs to the first analyzer. Additionally, a combination of fuzzy logic and statistical regression analyzers are provided to better model the equipment and the maintenance process. An optimizer with a bi-modal optimization process which integrates discrete maintenance events with continuous process variables is also provided. The optimizer determines the time and the type of maintenance activities which are to be executed, as well as the extent to which the maintenance activities can be postponed by changing other process variables. Thus, potential modifications to process variables are determined to improve the current performance of the processing equipment as it drifts out of tolerance.
摘要翻译：提供具有一系列滤波器的第一模型或第一分析器来表示维护事件的时变效应。第一模型或分析器进一步增强了用作第一分析器的输入的导出变量的选择。此外，还提供了模糊逻辑和统计回归分析器的组合，以更好地建模设备和维护过程。还提供了具有将离散维护事件与连续过程变量集成在一起的双模优化过程的优化器。优化器确定要执行的维护活动的时间和类型，以及通过更改其他过程变量可以推迟维护活动的程度。因此，确定对过程变量的潜在修改，以改善处理设备偏离公差的当前性能。

3. 发明授权

US5809490A Apparatus and method for selecting a working data set for model development 失效
标题翻译：用于选择模型开发的工作数据集的装置和方法
公开(公告)号：US5809490A
公开(公告)日：1998-09-15
申请号：US642779
申请日：1996-05-03
申请人： John P. Guiver , Casimir C. Klimasauskas
发明人： John P. Guiver , Casimir C. Klimasauskas
IPC分类号： G06K9/62 , G06N3/08 , G06F15/18
CPC分类号： G06K9/6251 , G06K9/6256 , G06K9/6262 , G06K9/6298 , G06N3/08
摘要： The present invention provides a data selection apparatus which augments a set of training examples with the desired output data. The resulting augmented data set is normalized such that the augmented data values range between -1 and +1 and such that the mean of the augmented data set is zero. The data selection apparatus then groups the augmented and normalized data set into related clusters using a clusterizer. Preferably, the clusterizer is a neural network such as a Kohonen self-organizing map (SOM). The data selection apparatus further applies an extractor to cull a working set of data from the clusterized data set. The present invention thus picks, or filters, a set of data which is more nearly uniformly distributed across the portion of the input space of interest to minimize the maximum absolute error over the entire input space. The output of the data selection apparatus is provided to train the analyzer with important sub-sets of the training data rather than with all available training data. A smaller training data set significantly reduces the complexity of the model building or analyzer construction process.
摘要翻译：本发明提供了一种数据选择装置，其增加具有所需输出数据的一组训练示例。所得到的增强数据集被归一化，使得增强的数据值范围在-1和+1之间，并且使得增强数据集的平均值为零。然后，数据选择装置使用聚类器将增强和归一化的数据集合分组成相关的簇。优选地，聚类器是诸如Kohonen自组织图（SOM）的神经网络。数据选择装置还应用提取器从集群数据集中剔除一组工作数据。因此，本发明选择或过滤一组更接近均匀分布在感兴趣的输入空间的部分上的数据，以最小化整个输入空间的最大绝对误差。数据选择装置的输出被提供来训练分析器具有训练数据的重要子集，而不是所有可用的训练数据。较小的训练数据集显着降低了建模模型或分析仪构建过程的复杂性。

4. 发明授权

US06246972B1 Analyzer for modeling and optimizing maintenance operations 有权
标题翻译：用于建模和优化维护操作的分析仪
公开(公告)号：US06246972B1
公开(公告)日：2001-06-12
申请号：US09321145
申请日：1999-05-27
申请人： Casimir C. Klimasauskas
发明人： Casimir C. Klimasauskas
IPC分类号： G06F1900
CPC分类号： G05B13/0275
摘要： A first model or first analyzer having a series of filters is provided to represent time-varying effects of maintenance events. The first model or analyzer further enhances the selection of derived variables which are used as inputs to the first analyzer. Additionally, a combination of fuzzy logic and statistical regression analyzers are provided to better model the equipment and the maintenance process. An optimizer with a bi-modal optimization process which integrates discrete maintenance events with continuous process variables is also provided. The optimizer determines the time and the type of maintenance activities which are to be executed, as well as the extent to which the maintenance activities can be postponed by changing other process variables. Thus, potential modifications to process variables are determined to improve the current performance of the processing equipment as it drifts out of tolerance.
摘要翻译：提供具有一系列滤波器的第一模型或第一分析器来表示维护事件的时变效应。第一模型或分析器进一步增强了用作第一分析器的输入的导出变量的选择。此外，还提供了模糊逻辑和统计回归分析器的组合，以更好地建模设备和维护过程。还提供了具有将离散维护事件与连续过程变量集成在一起的双模优化过程的优化器。优化器确定要执行的维护活动的时间和类型，以及通过更改其他过程变量可以推迟维护活动的程度。因此，确定对过程变量的潜在修改，以改善处理设备偏离公差的当前性能。

5. 发明授权

US5877954A Hybrid linear-neural network process control 失效
标题翻译：混合线性神经网络过程控制
公开(公告)号：US5877954A
公开(公告)日：1999-03-02
申请号：US642775
申请日：1996-05-03
申请人： Casimir C. Klimasauskas , John P. Guiver
发明人： Casimir C. Klimasauskas , John P. Guiver
IPC分类号： G05B13/02 , G05B19/042 , G05B13/04
CPC分类号： G05B19/042 , G05B13/027 , G05B13/0275
摘要： A hybrid analyzer having a data derived primary analyzer and an error correction analyzer connected in parallel is disclosed. The primary analyzer, preferably a data derived linear model such as a partial least squares model, is trained using training data to generate major predictions of defined output variables. The error correction analyzer, preferably a neural network model is trained to capture the residuals between the primary analyzer outputs and the target process variables. The residuals generated by the error correction analyzer is summed with the output of the primary analyzer to compensate for the error residuals of the primary analyzer to arrive at a more accurate overall model of the target process. Additionally, an adaptive filter can be applied to the output of the primary analyzer to further capture the process dynamics. The data derived hybrid analyzer provides a readily adaptable framework to build the process model without requiring up-front knowledge. Additionally, the primary analyzer, which incorporates the PLS model, is well accepted by process control engineers. Further, the hybrid analyzer also addresses the reliability of the process model output over the operating range since the primary analyzer can extrapolate data in a predictable way beyond the data used to train the model. Together, the primary and the error correction analyzers provide a more accurate hybrid process analyzer which mitigates the disadvantages, and enhances the advantages, of each modeling methodology when used alone.
摘要翻译：公开了一种具有数据导出的主分析器和并联连接的纠错分析仪的混合分析器。使用训练数据来训练主分析器，优选地是数据导出的线性模型，例如偏最小二乘模型，以产生定义的输出变量的主要预测。训练误差校正分析器，优选神经网络模型，以捕获主分析器输出和目标过程变量之间的残差。误差校正分析仪产生的残差与主分析仪的输出相加，以补偿主分析仪的误差残差，从而获得更准确的目标过程总体模型。此外，自适应滤波器可以应用于主分析仪的输出，以进一步捕获过程动态。数据导出的混合分析仪提供了一个易于适应的框架来构建过程模型，而不需要前期知识。此外，采用PLS模型的主分析仪被过程控制工程师所接受。此外，混合分析器还解决了在操作范围内的过程模型输出的可靠性，因为主分析器可以以可预测的方式外推数据，超出用于训练模型的数据。一起，主要和纠错分析仪一起提供了更精确的混合过程分析仪，可以减轻每个建模方法在单独使用时的缺点，并增强其优点。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式