公开(公告)号：US07640067B2

公开(公告)日：2009-12-29

申请号：US11004837

申请日：2004-12-07

申请人： Scott A. Boyden ,  Stephen Piche

发明人： Scott A. Boyden ,  Stephen Piche

IPC分类号： G05B13/02 ,  G05B21/00 ,  G06F7/00 ,  G06F17/00 ,  F01N3/00 ,  G01N30/96 ,  B01D50/00 ,  B01D53/34 ,  B01D53/86 ,  F23J11/00 ,  C01B21/00 ,  C01B17/00

CPC分类号： G05B13/027 ,  B01D2257/302 ,  B01D2257/404 ,  G05B13/048 ,  Y10T436/12

摘要： A controller directs a process primarily performed to control emission of a particular pollutant into the air. The process has multiple process parameters (MPPs), including a parameter representing an amount of the particular pollutant. The controller includes either a neural network process model or a non-neural network process model. In either case, the model represents a relationship between a first of the MPPs and one or more of the other MPPs. The one or more other MPPs include a second of the MPPs which is other than the parameter representing the amount of the emitted particular pollutant. Also included is a processor configured with logic to estimate a value of the second MPP, and to direct control of the first MPP based on the estimated value of the second MPP and the model.

摘要翻译： 控制器指导主要执行的过程，以将特定污染物的排放控制在空气中。 该过程具有多个过程参数（MPP），包括表示特定污染物量的参数。 控制器包括神经网络过程模型或非神经网络过程模型。 在任一情况下，模型表示第一MPP与一个或多个其他MPP之间的关系。 一个或多个其他MPP包括MPP中的第二个，其不同于表示所发射的特定污染物的量的参数。 还包括配置有用于估计第二MPP的值的逻辑的处理器，以及基于第二MPP和模型的估计值来直接控制第一MPP。

公开(公告)号：US07624079B2

公开(公告)日：2009-11-24

申请号：US11396486

申请日：2006-04-03

申请人： Eric Jon Hartman ,  Stephen Piche ,  Mark Gerules

发明人： Eric Jon Hartman ,  Stephen Piche ,  Mark Gerules

IPC分类号： G06E1/00 ,  G06E3/00

CPC分类号： G06N3/02 ,  G05B13/027 ,  G05B13/042 ,  G05B13/048 ,  G05B17/02

摘要： Method and apparatus for training a system model with gain constraints. A method is disclosed for training a steady-state model, the model having an input and an output and a mapping layer for mapping the input to the output through a stored representation of a system. A training data set is provided having a set of input data u(t) and target output data y(t) representative of the operation of a system. The model is trained with a predetermined training algorithm which is constrained to maintain the sensitivity of the output with respect to the input substantially within user defined constraint bounds by iteratively minimizing an objective function as a function of a data objective and a constraint objective. The data objective has a data fitting learning rate and the constraint objective has constraint learning rate that are varied as a function of the values of the data objective and the constraint objective after selective iterative steps.

摘要翻译： 用于训练具有增益约束的系统模型的方法和装置。 公开了一种用于训练稳态模型的方法，该模型具有输入和输出以及用于通过存储的系统表示将输入映射到输出的映射层。 提供具有代表系统的操作的一组输入数据u（t）和目标输出数据y（t）的训练数据集。 用预定的训练算法来训练该模型，该训练算法被约束以通过将作为数据目标和约束目标的函数的目标函数迭代地最小化来维持相对于基本上在用户定义的约束边界内的输入的输出的灵敏度。 数据目标具有数据拟合学习率，并且约束目标具有约束学习速率，其作为数据目标的值和选择性迭代步骤之后的约束目标的函数而变化。

公开(公告)号：US20070250215A1

公开(公告)日：2007-10-25

申请号：US11380084

申请日：2006-04-25

申请人： Jianhu Jia ,  Stephen Piche ,  W. Beaver

发明人： Jianhu Jia ,  Stephen Piche ,  W. Beaver

IPC分类号： G05B21/00

CPC分类号： G05B13/048

摘要： A method and apparatus for optimizing air flow to a boiler of a power generating unit using advanced optimization, modeling, and control techniques. Air flow is optimized to maintain flame stability, minimize air pollution emissions, and improve efficiency.

摘要翻译： 一种使用先进的优化，建模和控制技术优化到发电单元的锅炉的空气流量的方法和装置。 优化气流以保持火焰稳定性，最大​​限度减少空气污染排放，提高效率。

公开(公告)号：US07050866B2

公开(公告)日：2006-05-23

申请号：US10847211

申请日：2004-05-17

申请人： Gregory D. Martin ,  Eugene Boe ,  Stephen Piche ,  James David Keeler ,  Douglas Timmer ,  Mark Gerules ,  John P. Havener

发明人： Gregory D. Martin ,  Eugene Boe ,  Stephen Piche ,  James David Keeler ,  Douglas Timmer ,  Mark Gerules ,  John P. Havener

IPC分类号： G05B13/02

CPC分类号： G05B17/02 ,  G05B13/048

摘要： A method for providing independent static and dynamic models in a prediction, control and optimization environment utilizes an independent static model (20) and an independent dynamic model (22). The static model (20) is a rigorous predictive model that is trained over a wide range of data, whereas the dynamic model (22) is trained over a narrow range of data. The gain K of the static model (20) is utilized to scale the gain k of the dynamic model (22). The forced dynamic portion of the model (22) referred to as the bi variables are scaled by the ratio of the gains K and k. The bi have a direct effect on the gain of a dynamic model (22). This is facilitated by a coefficient modification block (40). Thereafter, the difference between the new value input to the static model (20) and the prior steady-state value is utilized as an input to the dynamic model (22). The predicted dynamic output is then summed with the previous steady-state value to provide a predicted value Y. Additionally, the path that is traversed between steady-state value changes.

摘要翻译： 在预测，控制和优化环境中提供独立的静态和动态模型的方法使用独立的静态模型（20）和独立的动态模型（22）。 静态模型（20）是一种严格的预测模型，可在广泛的数据范围内进行训练，而动态模型（22）则是在窄范围的数据上进行训练。 使用静态模型（20）的增益K来缩放动态模型（22）的增益k。 被称为变量的模型（22）的强制动态部分通过增益K和k的比率来缩放。 b）对动态模型（22）的增益有直接的影响。 这通过系数修改块（40）来促进。 此后，将输入到静态模型（20）的新值与先前稳态值之间的差用作动态模型（22）的输入。 然后将预测的动态输出与先前的稳态值相加以提供预测值Y.此外，在稳态值变化之间经过的路径。

公开(公告)号：US07047089B2

公开(公告)日：2006-05-16

申请号：US10843160

申请日：2004-05-11

申请人： Gregory D. Martin ,  Eugene Boe ,  Stephen Piche ,  James David Keeler ,  Douglas Timmer ,  Mark Gerules ,  John P. Havener

发明人： Gregory D. Martin ,  Eugene Boe ,  Stephen Piche ,  James David Keeler ,  Douglas Timmer ,  Mark Gerules ,  John P. Havener

IPC分类号： G05B13/02

CPC分类号： G05B13/048 ,  G05B13/042 ,  G05B17/02

摘要： A method and apparatus for controlling a non-linear mill. A linear controller is provided having a linear gain k that is operable to receive inputs representing measured variables of the plant and predict on an output of the linear controller predicted control values for manipulatible variables that control the plant. A non-linear model of the plant is provided for storing a representation of the plant over a trained region of the operating input space and having a steady-state gain K associated therewith. The gain k of the linear model is adjusted with the gain K of the non-linear model in accordance with a predetermined relationship as the measured variables change the operating region of the input space at which the linear controller is predicting the values for the manipulatible variables. The predicted manipulatible variables are then output after the step of adjusting the gain k.

公开(公告)号：US20060100721A1

公开(公告)日：2006-05-11

申请号：US10982139

申请日：2004-11-05

申请人： Stephen Piche

发明人： Stephen Piche

IPC分类号： G05B13/02

CPC分类号： G05B13/048 ,  G05B5/01 ,  G05B13/027

摘要： Non-linear model with disturbance rejection. A method for training a non linear model for predicting an output parameter of a system is disclosed that operates in an environment having associated therewith slow varying and unmeasurable disturbances. An input layer is provided having a plurality of inputs and an output layer is provided having at least one output for providing the output parameter. A data set of historical data taken over a time line at periodic intervals is generated for use in training the model. The model is operable to map the input layer through a stored representation to the output layer. Training of the model involves training the stored representation on the historical data set to provide rejection of the disturbances in the stored representation.

公开(公告)号：US20060058899A1

公开(公告)日：2006-03-16

申请号：US10926991

申请日：2004-08-27

申请人： Scott Boyden ,  Stephen Piche

发明人： Scott Boyden ,  Stephen Piche

IPC分类号： G05B13/02

CPC分类号： G05B13/026 ,  B01D53/30 ,  B01D2257/302 ,  B01D2257/404 ,  G05B13/021

摘要： A multi-tier controller directs operation of a system performing a process. The process has multiple process parameters (MPPs), at least one of the MPPs being a controllable process parameter (CTPP) and one of the MPPs being a targeted process parameter (TPP). The process also has a defined target limit (DTV) representing a first limit on an actual average value (MV) of the TPP over a defined time period of length TPLAAV2. The AAV is computed based on actual values (AVs) of the TPP over the defined period. A first logical controller predicts future average values (FAVs) of the TPP over a first future time period (FFTP) having a length of at least TPLAAV2 and extending from a current time T0 to an future time TAAV2, prior to which the TPP will move to steady state. The FAVs are predicted based on (i) the AAVs of the TPP at various times over a first prior time period (FPTP) having a length of at least TPLAAV2 and extending from a prior time of T-AAV2 to the current time T0, (ii) the current values of the MPPs, and (iii) the DTV. A second logical controller establishes a further target limit (FTV) representing a second limit on the MV of the TPP for a second future time period (SFTP) having a length equal to TPLAAV2, which is less than the length TPLAAV2, and extending from the current time T0 to a future time TAAV1. The FTV is established based on one or more of the predicted FAVs of the TPP over the FFTP. The second logical controller also determines a target set point for each CTPP based on (i) the AAVs of the TPP at various times over a second prior time period (SPTP) having the length TPLAAV1 and extending from a prior time T-AAV1 to the current time T0, (ii) the current values of the MPPs, and (iii) the FTV. The second logical controller additionally has logic to direct control of each CTPP in accordance with the determined target set point for that CTPP.

公开(公告)号：US20060047347A1

公开(公告)日：2006-03-02

申请号：US10927201

申请日：2004-08-27

申请人： Scott Boyden ,  Stephen Piche

发明人： Scott Boyden ,  Stephen Piche

IPC分类号： G05B11/01

CPC分类号： G05B13/048

摘要： A controller directs performance of a process having multiple process parameters (MPPs), including a controllable process parameter (CTPP), a targeted process parameter (TPP), a defined target value (DTV) representing a limit on an actual average value (AAV) of the TPP over a defined moving time period of length TPLAAV. A storage device stores historical data representing the AVs of the TPP at various times over a prior time period (PTP) having a length of at least TPLAAV. A processor predicts future average values (FAVs) of the TPP over a future time period (FTP) based on the stored historical data and the current values of the MPPs. The processor also determines a target set point for each CTPP based on the predicted FAVs, the current values of the MPPs and the DTV, and directs control of each CTPP in accordance with the determined target set point for that CTPP.

公开(公告)号：US20060045800A1

公开(公告)日：2006-03-02

申请号：US10927229

申请日：2004-08-27

申请人： Scott Boyden ,  Stephen Piche

发明人： Scott Boyden ,  Stephen Piche

IPC分类号： G05D7/00

CPC分类号： G05B13/024 ,  B01D53/346 ,  B01D53/8696 ,  B01D2257/302 ,  B01D2257/404

摘要： A controller directs operation of an air pollution control (APC) system performing a process to control emissions of a pollutant. The process has multiple process parameters (MPPs), one or more of the MPPs being a controllable process parameters (CTPPs) and one of the MPPs being an amount of the pollutant (AOP) emitted by the system. A user input device identifies an optimization objective. A control processor determines a set point for at least one of the one or more CTPPs based on the current values of the MPPs and the identified optimization objective, and directs control of one of the at least one CTPP based on the determined set point for that CTPP.

公开(公告)号：US20050075737A1

公开(公告)日：2005-04-07

申请号：US10847211

申请日：2004-05-17

申请人： Gregory Martin ,  Eugene Boe ,  Stephen Piche ,  James Keeler ,  Douglas Timmer ,  Mark Gerules ,  John Havener

发明人： Gregory Martin ,  Eugene Boe ,  Stephen Piche ,  James Keeler ,  Douglas Timmer ,  Mark Gerules ,  John Havener

IPC分类号： G05B13/02 ,  G05B13/04 ,  G05B17/02 ,  G05B21/02

CPC分类号： G05B17/02 ,  G05B13/048

摘要： A method for providing independent static and dynamic models in a prediction, control and optimization environment utilizes an independent static model (20) and an independent dynamic model (22). The static model (20) is a rigorous predictive model that is trained over a wide range of data, whereas the dynamic model (22) is trained over a narrow range of data. The gain K of the static model (20) is utilized to scale the gain k of the dynamic model (22). The forced dynamic portion of the model (22) referred to as the bi variables are scaled by the ratio of the gains K and k. The bi have a direct effect on the gain of a dynamic model (22). This is facilitated by a coefficient modification block (40). Thereafter, the difference between the new value input to the static model (20) and the prior steady-state value is utilized as an input to the dynamic model (22). The predicted dynamic output is then summed with the previous steady-state value to provide a predicted value Y. Additionally, the path that is traversed between steady-state value changes.

摘要翻译： 在预测，控制和优化环境中提供独立的静态和动态模型的方法使用独立的静态模型（20）和独立的动态模型（22）。 静态模型（20）是一种严格的预测模型，可在广泛的数据范围内进行训练，而动态模型（22）则是在窄范围的数据上进行训练。 使用静态模型（20）的增益K来缩放动态模型（22）的增益k。 被称为双变量的模型（22）的强制动态部分通过增益K和k的比率来缩放。 bi对动态模型的获得有直接的影响（22）。 这通过系数修改块（40）来促进。 此后，将输入到静态模型（20）的新值与先前稳态值之间的差用作动态模型（22）的输入。 然后将预测的动态输出与先前的稳态值相加以提供预测值Y.此外，在稳态值变化之间经过的路径。