公开(公告)号：US20150301510A1

公开(公告)日：2015-10-22

申请号：US14258740

申请日：2014-04-22

申请人： Siegmund Düll ,  Mrinal Munshi ,  Sigurd Spieckermann ,  Steffen Udluft

发明人： Siegmund Düll ,  Mrinal Munshi ,  Sigurd Spieckermann ,  Steffen Udluft

IPC分类号： G05B15/02 ,  G06N3/08

CPC分类号： G06N3/08 ,  G05B13/027

摘要： For controlling a target system, operational data of a plurality of source systems are used. The data of the source systems are received and are distinguished by source system specific identifiers. By a neural network, a neural model is trained on the basis of the received operational data of the source systems taking into account the source system specific identifiers, where a first neural model component is trained on properties shared by the source systems and a second neural model component is trained on properties varying between the source systems. After receiving operational data of the target system, the trained neural model is further trained on the basis of the operational data of the target system, where a further training of the second neural model component is given preference over a further training of the first neural model component. The target system is controlled by the further trained neural network.

摘要翻译： 为了控制目标系统，使用多个源系统的操作数据。 源系统的数据被接收并由源系统特定标识符区分。 通过神经网络，在考虑到源系统特定标识符的基础上，基于接收到的源系统的操作数据来训练神经模型，其中第一神经模型分量被训练在源系统共享的属性上，第二神经模型 对源代码系统之间的属性进行训练。 在接收目标系统的操作数据之后，基于目标系统的操作数据进一步训练经过训练的神经模型，其中第二神经模型组件的进一步训练优先于第一神经模型的进一步训练 零件。 目标系统由进一步训练的神经网络控制。

公开(公告)号：US20130013543A1

公开(公告)日：2013-01-10

申请号：US13583057

申请日：2011-02-15

申请人： Siegmund Düll ,  Volkmar Sterzing ,  Steffen Udluft

发明人： Siegmund Düll ,  Volkmar Sterzing ,  Steffen Udluft

IPC分类号： G06N3/08

CPC分类号： G05B13/027

摘要： A method for the computer-aided control of a technical system is provided. A recurrent neuronal network is used for modeling the dynamic behaviour of the technical system, the input layer of which contains states of the technical system and actions carried out on the technical system, which are supplied to a recurrent hidden layer. The output layer of the recurrent neuronal network is represented by an evaluation signal which reproduces the dynamics of technical system. The hidden states generated using the recurrent neural network are used to control the technical system on the basis of a learning and/or optimization method.

摘要翻译： 提供了一种用于技术系统的计算机辅助控制的方法。 复发神经元网络用于对技术系统的动态行为进行建模，其技术系统的输入层包含技术系统的状态和在技术系统上执行的动作，并提供给复发隐藏层。 复发神经元网络的输出层由再现动态技术系统的评估信号表示。 使用循环神经网络产生的隐藏状态用于在学习和/或优化方法的基础上控制技术系统。

公开(公告)号：US09489619B2

公开(公告)日：2016-11-08

申请号：US13992799

申请日：2011-11-16

申请人： Siegmund Düll ,  Alexander Hans ,  Steffen Udluft

发明人： Siegmund Düll ,  Alexander Hans ,  Steffen Udluft

IPC分类号： G06F15/18 ,  G06N3/08 ,  G06N3/04

CPC分类号： G06N3/08 ,  G06N3/0445

摘要： A method for computer-assisted modeling of a technical system is disclosed. At multiple different operating points, the technical system is described by a first state vector with first state variable(s) and by a second state vector with second state variable(s). A neural network comprising a special form of a feed-forward network is used for the computer-assisted modeling of said system. The feed-forward network includes at least one bridging connector that connects a neural layer with an output layer, thereby bridging at least one hidden layer, which allows the training of networks with multiple hidden layers in a simple manner with known learning methods, e.g., the gradient descent method. The method may be used for modeling a gas turbine system, in which a neural network trained using the method may be used to estimate or predict nitrogen oxide or carbon monoxide emissions or parameters relating to combustion chamber vibrations.

摘要翻译： 公开了一种技术系统的计算机辅助建模方法。 在多个不同的操作点，技术系统由具有第一状态变量的第一状态向量和具有第二状态变量的第二状态向量描述。 包括前馈网络的特殊形式的神经网络用于所述系统的计算机辅助建模。 前馈网络包括至少一个桥接连接器，其将神经层与输出层相连，从而桥接至少一个隐藏层，这允许以已知的学习方法以简单的方式训练具有多个隐藏层的网络，例如， 梯度下降法。 该方法可以用于对燃气轮机系统进行建模，其中使用该方法训练的神经网络可以用于估计或预测氮氧化物或一氧化碳排放物或与燃烧室振动相关的参数。

公开(公告)号：US20130282635A1

公开(公告)日：2013-10-24

申请号：US13992799

申请日：2011-11-16

申请人： Siegmund Düll ,  Alexander Hans ,  Steffen Udluft

发明人： Siegmund Düll ,  Alexander Hans ,  Steffen Udluft

IPC分类号： G06N3/08

CPC分类号： G06N3/08 ,  G06N3/0445

摘要： A method for computer-assisted modeling of a technical system is disclosed. At multiple different operating points, the technical system is described by a first state vector with first state variable(s) and by a second state vector with second state variable(s). A neural network comprising a special form of a feed-forward network is used for the computer-assisted modeling of said system. The feed-forward network includes at least one bridging connector that connects a neural layer with an output layer, thereby bridging at least one hidden layer, which allows the training of networks with multiple hidden layers in a simple manner with known learning methods, e.g., the gradient descent method. The method may be used for modeling a gas turbine system, in which a neural network trained using the method may be used to estimate or predict nitrogen oxide or carbon monoxide emissions or parameters relating to combustion chamber vibrations.

摘要翻译： 公开了一种技术系统的计算机辅助建模方法。 在多个不同的操作点，技术系统由具有第一状态变量的第一状态向量和具有第二状态变量的第二状态向量描述。 包括前馈网络的特殊形式的神经网络用于所述系统的计算机辅助建模。 前馈网络包括至少一个桥接连接器，其将神经层与输出层相连，从而桥接至少一个隐藏层，这允许以已知的学习方法以简单的方式训练具有多个隐藏层的网络，例如， 梯度下降法。 该方法可以用于对燃气轮机系统进行建模，其中使用该方法训练的神经网络可以用于估计或预测氮氧化物或一氧化碳排放物或与燃烧室振动相关的参数。

公开(公告)号：US09466032B2

公开(公告)日：2016-10-11

申请号：US14123401

申请日：2012-06-01

申请人： Siegmund Düll ,  Alexander Hentschel ,  Volkmar Sterzing ,  Steffen Udluft

发明人： Siegmund Düll ,  Alexander Hentschel ,  Volkmar Sterzing ,  Steffen Udluft

IPC分类号： G06F19/00 ,  G06N99/00 ,  G05B17/02 ,  G05B23/02 ,  G05B13/04 ,  G06N3/04

CPC分类号： G06N99/005 ,  F03D7/046 ,  F03D17/00 ,  G05B13/04 ,  G05B17/02 ,  G05B23/024 ,  G06N3/0481 ,  Y02E10/723

摘要： A method for the computer-supported generation of a data-driven model of a technical system, in particular of a gas turbine or wind turbine, based on training data is disclosed. The data-driven model is preferably learned in regions of training data having a low data density. According to the invention, it is thus ensured that the data-driven model is generated for information-relevant regions of the training data. The data-driven model generated is used in a particularly preferred embodiment for calculating a suitable control and/or regulation model or monitoring model for the technical system. By determining optimization criteria, such as low pollutant emissions or low combustion dynamics of a gas turbine, the service life of the technical system in operation can be extended. The data model generated by the method according to the invention can furthermore be determined quickly and using low computing resources, since not all training data is used for learning the data-driven model.

摘要翻译： 公开了一种基于训练数据计算机支持生成技术系统，特别是燃气轮机或风力涡轮机的数据驱动模型的方法。 优选地，在具有低数据密度的训练数据的区域中学习数据驱动模型。 根据本发明，确保为训练数据的信息相关区域生成数据驱动模型。 在特别优选的实施例中使用产生的数据驱动模型来计算技术系统的合适的控制和/或调节模型或监控模型。 通过确定燃气轮机低污染物排放或低燃烧动力学等优化标准，可以延长运行中的技术系统的使用寿命。 由于不是所有的训练数据都用于学习数据驱动的模型，因此可以快速确定根据本发明的方法生成的数据模型并使用低计算资源。

公开(公告)号：US20150370227A1

公开(公告)日：2015-12-24

申请号：US14309641

申请日：2014-06-19

申请人： Hany F. Bassily ,  Clemens Otte ,  Siegmund Düll ,  Michael Müller ,  Steffen Udluft

发明人： Hany F. Bassily ,  Clemens Otte ,  Siegmund Düll ,  Michael Müller ,  Steffen Udluft

IPC分类号： G05B13/02

CPC分类号： G05B13/027

摘要： For controlling a target system, such as a gas or wind turbine or another technical system, a pool of control policies is used. The pool of control policies including a plurality of control policies and weights for weighting each control policy of the plurality of control policies are received. The plurality of control policies is weighted by the weights to provide a weighted aggregated control policy. The target system is controlled using the weighted aggregated control policy, and performance data relating to a performance of the controlled target system is received. The weights are adjusted based on the received performance data to improve the performance of the controlled target system. The plurality of control policies is reweighted by the adjusted weights to adjust the weighted aggregated control policy.

摘要翻译： 为了控制诸如气体或风力涡轮机或其他技术系统的目标系统，使用一组控制策略。 接收包括用于对多个控制策略的每个控制策略加权的多个控制策略和权重的控制策略池。 多个控制策略由权重加权以提供加权聚合控制策略。 使用加权聚合控制策略控制目标系统，并且接收与受控对象系统的性能相关的性能数据。 基于所接收的性能数据来调整权重以改善受控目标系统的性能。 多个控制政策通过调整权重重新加权，以调整加权汇总控制策略。

公开(公告)号：US20140100703A1

公开(公告)日：2014-04-10

申请号：US14123401

申请日：2012-06-01

申请人： Siegmund Düll ,  Alexander Hentschel ,  Volkmar Sterzing ,  Steffen Udluft

发明人： Siegmund Düll ,  Alexander Hentschel ,  Volkmar Sterzing ,  Steffen Udluft

IPC分类号： G06N99/00 ,  G05B13/04

CPC分类号： G06N99/005 ,  F03D7/046 ,  F03D17/00 ,  G05B13/04 ,  G05B17/02 ,  G05B23/024 ,  G06N3/0481 ,  Y02E10/723

摘要： A method for the computer-supported generation of a data-driven model of a technical system, in particular of a gas turbine or wind turbine, based on training data is disclosed. The data-driven model is preferably learned in regions of training data having a low data density. According to the invention, it is thus ensured that the data-driven model is generated for information-relevant regions of the training data. The data-driven model generated is used in a particularly preferred embodiment for calculating a suitable control and/or regulation model or monitoring model for the technical system. By determining optimization criteria, such as low pollutant emissions or low combustion dynamics of a gas turbine, the service life of the technical system in operation can be extended. The data model generated by the method according to the invention can furthermore be determined quickly and using low computing resources, since not all training data is used for learning the data-driven model.

摘要翻译： 公开了一种基于训练数据计算机支持生成技术系统，特别是燃气轮机或风力涡轮机的数据驱动模型的方法。 优选地，在具有低数据密度的训练数据的区域中学习数据驱动模型。 根据本发明，确保为训练数据的信息相关区域生成数据驱动模型。 在特别优选的实施例中使用产生的数据驱动模型来计算技术系统的合适的控制和/或调节模型或监控模型。 通过确定燃气轮机低污染物排放或低燃烧动力学等优化标准，可以延长运行中的技术系统的使用寿命。 由于不是所有的训练数据都用于学习数据驱动的模型，因此可以快速确定根据本发明的方法生成的数据模型并使用低计算资源。

公开(公告)号：US09194369B2

公开(公告)日：2015-11-24

申请号：US13550723

申请日：2012-07-17

申请人： Kristian Robert Dixon ,  Siegmund Düll ,  Per Egedal ,  Thomas Esbensen ,  Volkmar Sterzing

发明人： Kristian Robert Dixon ,  Siegmund Düll ,  Per Egedal ,  Thomas Esbensen ,  Volkmar Sterzing

IPC分类号： F03D1/06 ,  F03D7/02

CPC分类号： F03D7/022 ,  F03D1/0675 ,  F05B2240/30 ,  Y02E10/721 ,  Y02E10/723

摘要： A wind turbine rotor blade is equipped with an air chamber and equipped via the air chamber to route a modulation beam out of the rotor blade such that the air current along the rotor blade is changed. Thereby the laminar current is changed into a turbulent current on the one hand and its detachment and on the other hand its recreation is achieved in order to produce the laminar current. The control may occur via electrostatic actuators via a learnable control strategy based on neural forecasts, which take the complexity of the non-linear system into account and allow for the plurality of influencing factors. The stress on the rotor blades may be reduced, resulting in longer service life and reduced maintenance costs, a higher level of efficiency or quieter operation.

摘要翻译： 风力涡轮机转子叶片配备有空气室，并且经由空气室配置，以将调制光束从转子叶片引出，使得沿着转子叶片的气流被改变。 因此，一方面，层流变成湍流，并且其分离，另一方面实现其娱乐以产生层流。 该控制可以通过静电致动器通过基于神经预测的可学习的控制策略进行，其将非线性系统的复杂性考虑在内并允许多个影响因素。 可以减小转子叶片上的应力，从而延长使用寿命，降低维护成本，提高效率或更安静的操作。

公开(公告)号：US20130022464A1

公开(公告)日：2013-01-24

申请号：US13550723

申请日：2012-07-17

申请人： Kristian Robert Dixon ,  Siegmund Düll ,  Per Egedal ,  Thomas Esbensen ,  Volkmar Sterzing

发明人： Kristian Robert Dixon ,  Siegmund Düll ,  Per Egedal ,  Thomas Esbensen ,  Volkmar Sterzing

IPC分类号： F03D1/06 ,  F03D7/02

CPC分类号： F03D7/022 ,  F03D1/0675 ,  F05B2240/30 ,  Y02E10/721 ,  Y02E10/723

摘要： A wind turbine rotor blade is equipped with an air chamber and equipped via the air chamber to route a modulation beam out of the rotor blade such that the air current along the rotor blade is changed. Thereby the laminar current is changed into a turbulent current on the one hand and its detachment and on the other hand its recreation is achieved in order to produce the laminar current. The control may occur via electrostatic actuators via a learnable control strategy based on neural forecasts, which take the complexity of the non-linear system into account and allow for the plurality of influencing factors. The stress on the rotor blades may be reduced, resulting in longer service life and reduced maintenance costs, a higher level of efficiency or quieter operation.