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

US06745169B1 Learning process for a neural network 失效
标题翻译：神经网络的学习过程
公开(公告)号：US06745169B1
公开(公告)日：2004-06-01
申请号：US08686792
申请日：1996-07-26
申请人： Martin Schlang , Frank-Oliver Malisch , Einar Broese , Otto Gramckow
发明人： Martin Schlang , Frank-Oliver Malisch , Einar Broese , Otto Gramckow
IPC分类号： G06F1518
CPC分类号： B21B37/00 , B21B2265/12 , G05B13/027 , G06N3/08
摘要： A learning process for a neural network for open-loop or closed-loop control of an industrial process with time-variable parameters. The neural network is configured either as an open-loop or closed-loop-control network with which the process is controlled. The neural network is trained with the current process data so that it builds a model of the current process. The neural network can also be configured as a background network which is trained during operation with representative process data so that it builds an averaged model of the process over a longer period of time. After a certain learning time or upon the occurrence of an external event, the open-loop or closed-control network is replaced by the background network.
摘要翻译：用于具有时变参数的工业过程的开环或闭环控制的神经网络的学习过程。神经网络被配置为开环或闭环控制网络，过程被控制。神经网络使用当前的过程数据进行训练，从而构建当前过程的模型。神经网络还可以被配置为背景网络，其在具有代表性的过程数据的操作期间被训练，使得它在更长的时间段内构建过程的平均模型。在一定的学习时间之后或外部事件发生时，开环或闭路控制网络被后台网络所取代。

2. 发明授权

US5608842A Method and device for conducting a process in a controlled system with at least one precomputed parameter based on a plurality of results from partial mathematical models combined by a neural network 失效
标题翻译：用于基于来自由神经网络组合的部分数学模型的多个结果的至少一个预计算参数在受控系统中进行处理的方法和装置
公开(公告)号：US5608842A
公开(公告)日：1997-03-04
申请号：US336958
申请日：1994-11-10
申请人： Einar Broese , Otto Gramckow , Thomas Martinetz , Guenter Soergel
发明人： Einar Broese , Otto Gramckow , Thomas Martinetz , Guenter Soergel
IPC分类号： B21B37/00 , B21B37/28 , G05B13/02 , G05B13/04 , G05B17/02 , G05B23/02 , G06F15/18 , G06G7/60 , G06N3/00 , G06E1/00 , G06E3/00
CPC分类号： B21B37/28 , G05B13/027 , G05B17/02
摘要： In known methods for conducting a process in an automatically controlled system, the system is preset at the beginning of each process run according to at least one process parameter. The at least one process parameter is precomputed with a model of the process which is supplied with input values. During the process, the input values and the process parameters are measured and are used after the process run to adaptively improve the precomputed value of the process parameters. To simplify and improve the precomputed value of a model having a plurality of partial models, computed results of the partial models are supplied to a neural network. The neural network produces the process parameters to be precomputed as a network response. The network parameters of the neural network are modified after each process run to adapt the precomputed value to the actual process events.
摘要翻译：在用于在自动控制的系统中进行过程的已知方法中，系统根据至少一个过程参数在每个过程运行的开始处被预设。至少一个过程参数是用提供有输入值的过程的模型预先计算的。在此过程中，测量输入值和过程参数，并在过程运行后使用以自适应地改进过程参数的预计算值。为了简化和改进具有多个部分模型的模型的预计算值，将部分模型的计算结果提供给神经网络。神经网络产生要作为网络响应预先计算的过程参数。在每个过程运行之后修改神经网络的网络参数，以将预计算值适应于实际过程事件。

3. 发明授权

US5673368A Method and device for conducting a process in a controlled system with at least one precomputed process parameter determined using a mathematical model having variable model parameters adjusted based on a network response of a neural network 失效
标题翻译：用于使用具有基于神经网络的网络响应调整的可变模型参数的数学模型确定的至少一个预计算过程参数在受控系统中进行处理的方法和装置
公开(公告)号：US5673368A
公开(公告)日：1997-09-30
申请号：US336952
申请日：1994-11-10
申请人： Einar Broese , Otto Gramckow , Thomas Martinetz , Guenter Soergel
发明人： Einar Broese , Otto Gramckow , Thomas Martinetz , Guenter Soergel
IPC分类号： B21B37/00 , B21B37/74 , G05B13/02 , G05B13/04 , G05B23/02 , G06F15/18 , G06G7/60 , G06N3/00
CPC分类号： C21D11/005 , B21B37/00 , B21B37/74 , C21D11/00 , G05B13/027 , B21B2261/20 , Y10S706/903 , Y10S706/906
摘要： In known processes for conducting a process in an automatically controlled system, the system is preset at the beginning of each process run based on at least one process parameter. The at least one process parameter is precomputed with a model of the process, containing at least one model parameter and input values supplied to the model. During the process, the input values and the process parameter are measured and used to adaptively improve the precomputed process parameter after the process run. A neural network is used to determine the model parameters whose dependence on the input values is unknown or insufficiently known. Network parameters of the neural network are modified after each process run to adapt the model to the actual process events.
摘要翻译：在用于在自动控制的系统中进行过程的已知过程中，系统在每个过程运行开始时基于至少一个过程参数来预设。所述至少一个过程参数用所述过程的模型预先计算，所述模型包含提供给所述模型的至少一个模型参数和输入值。在此过程中，输入值和过程参数被测量并用于在过程运行后自适应地改进预计算过程参数。使用神经网络来确定其对输入值的依赖性未知或不充分的模型参数。每个过程运行后修改神经网络的网络参数，以使模型适应实际的过程事件。

4. 发明授权

US5600758A Method and device for conducting a process in a controlled system with at least one precomputed process parameter. 失效
标题翻译：用于利用至少一个预计算过程参数在受控系统中进行过程的方法和装置。
公开(公告)号：US5600758A
公开(公告)日：1997-02-04
申请号：US337660
申请日：1994-11-10
申请人： Einar Broese , Otto Gramckow , Thomas Martinetz , Guenter Soergel
发明人： Einar Broese , Otto Gramckow , Thomas Martinetz , Guenter Soergel
IPC分类号： B21B37/00 , B21B37/58 , B21B37/74 , G05B13/02 , G05B13/04 , G05B17/02 , G05B23/02 , G06F15/18 , G06G7/60 , G06N3/00 , G06E1/00 , G06E3/00
CPC分类号： B21B37/74 , B21B37/58 , G05B13/027 , G05B17/02
摘要： Known methods for conducting a process in an automatically controlled system preset the system at the beginning of each process run based on at least one process parameter. The process parameter is precomputed with a model of the process which is supplied with input values. During the process the input values and the process parameter are measured and are used to adaptively improve the precomputed process parameter after the process run. The present invention simplifies and improves the precomputed value of the process parameter by supplying at least part of the input values to a neural network. The network response of the neural network forms a correction value for the approximate value delivered by the model for the process parameter to be precomputed. The network parameters of the neural network are modified after each process run to adapt the precomputed value to the actual process events.
摘要翻译：在自动控制系统中执行过程的已知方法基于至少一个过程参数在每个过程运行开始时预设系统。过程参数使用输入值提供的过程模型进行预计算。在此过程中，测量输入值和过程参数，并在过程运行后用于自适应地改进预计算过程参数。本发明通过向神经网络提供至少一部分输入值来简化和改进过程参数的预计算值。神经网络的网络响应形成由模型提供的用于要预先计算的过程参数的近似值的校正值。在每个过程运行之后修改神经网络的网络参数，以将预计算值适应于实际过程事件。

5. 发明授权

US07085619B2 Method for controlling an industrial process 失效
标题翻译：控制工业过程的方法
公开(公告)号：US07085619B2
公开(公告)日：2006-08-01
申请号：US10503276
申请日：2003-01-16
申请人： Einar Broese , Klaus Weinzieri
发明人： Einar Broese , Klaus Weinzieri
IPC分类号： G06F19/00 , G05B13/04
CPC分类号： G05B13/042 , B21B1/26 , B21B37/76 , C21D11/005
摘要： The invention relates to a method for controlling an industrial process for manufacturing or processing a product, in particular for controlling the cooling line of a hot-rolling mill, said cooling line being simulated by a physical model. To optimize the cooling process, a correction factor is determined in a simple manner, whereby the product data records are saved with the correction factors that have been determined previously. For a new strip to be cooled, the saved product data records are compared with the product data of the new strip and similar data records are extracted. A new correction factor is then determined, e.g. by means of linear regression, from the correction factors of the similar product data records.
摘要翻译：本发明涉及一种用于控制用于制造或加工产品的工业过程的方法，特别是用于控制热轧机的冷却管线，所述冷却管线由物理模型模拟。为了优化冷却过程，以简单的方式确定校正因子，由此产品数据记录与先前已经确定的校正因子一起被保存。对于要冷却的新条，将保存的产品数据记录与新条带的产品数据进行比较，并提取类似的数据记录。然后确定新的校正因子，例如。通过线性回归，从类似产品数据记录的校正因子。

6. 发明授权

US06722173B2 Method and device for determining the rolling force in a roll stand 有权
标题翻译：用于确定轧辊架中的轧制力的方法和装置
公开(公告)号：US06722173B2
公开(公告)日：2004-04-20
申请号：US09962370
申请日：2001-09-24
申请人： Einar Broese , Bjoern Feldkeller , Thomas Peuker , Thomas Poppe
发明人： Einar Broese , Bjoern Feldkeller , Thomas Peuker , Thomas Poppe
IPC分类号： B21B3716
CPC分类号： G05B17/02 , B21B37/58 , B21B38/08 , B21B2265/12
摘要： In a method for determining the rolling force in a roll stand for rolling metallic material which is to be rolled, the rolling force is determined by means of at least one neural network. According to the invention, the neural network is trained using, in particular measured, values for the rolling force under different operating conditions with a view to improving the determination of the rolling force. The neural network is advantageously trained using values for the rolling force and values for the different operating conditions for roll stands of different rolling trains.
摘要翻译：在用于确定用于滚动待轧制的金属材料的辊架中的轧制力的方法中，通过至少一个神经网络来确定轧制力。根据本发明，为了改善滚动力的确定，使用特别是测量的不同操作条件下的滚动力值来训练神经网络。利用滚动力的值和不同轧制列车的轧辊架的不同工作条件的值来训练神经网络。

7. 发明申请

US20050131572A1 Method for controlling an industrial process 失效
标题翻译：控制工业过程的方法
公开(公告)号：US20050131572A1
公开(公告)日：2005-06-16
申请号：US10503276
申请日：2003-01-16
申请人： Einar Broese , Klaus Weinzieri
发明人： Einar Broese , Klaus Weinzieri
IPC分类号： B21B45/02 , B21B1/26 , B21B37/76 , C21D11/00 , G05B13/04 , G06F19/00
CPC分类号： G05B13/042 , B21B1/26 , B21B37/76 , C21D11/005
摘要： The invention relates to a method for controlling an industrial process for manufacturing or processing a product, in particular for controlling the cooling line of a hot-rolling mill, said cooling line being simulated by a physical model. To optimize the cooling process, a correction factor is determined in a simple manner, whereby the product data records are saved with the correction factors that have been determined previously. For a new strip to be cooled, the saved product data records are compared with the product data of the new strip and similar data records are extracted. A new correction factor is then determined, e.g. by means of linear regression, from the correction factors of the similar product data records.
摘要翻译：本发明涉及一种用于控制用于制造或加工产品的工业过程的方法，特别是用于控制热轧机的冷却管线，所述冷却管线由物理模型模拟。为了优化冷却过程，以简单的方式确定校正因子，由此产品数据记录与先前已经确定的校正因子一起被保存。对于要冷却的新条，将保存的产品数据记录与新条带的产品数据进行比较，并提取类似的数据记录。然后确定新的校正因子，例如。通过线性回归，从类似产品数据记录的校正因子。

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