Patents by Inventor Amit Chakraborty

Amit Chakraborty has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20160020608
    Abstract: A method (100) for electricity demand shaping through load shedding and shifting in an electrical smart grid.
    Type: Application
    Filed: March 5, 2014
    Publication date: January 21, 2016
    Inventors: Rodrigo Carrasco, Ioannis Akrotirianakis, Amit Chakraborty
  • Publication number: 20150262083
    Abstract: The Support Vector Machine (SVM) has been used in a wide variety of classification problems. The original SVM uses the hinge loss function, which is nondifferentiable and makes the problem difficult to solve in particular for regularized SVMs, such as with l1-norm. The Huberized SVM (HSVM) is considered, which uses a differentiable approximation of the hinge loss function. The Proximal Gradient (PG) method is used to solving binary-class HSVM (BHSVM) and then generalized to multi-class HSVM (MHSVM). Under strong convexity assumptions, the algorithm converges linearly. A finite convergence result about the support of the solution is given, based on which the algorithm is further accelerated by a two-stage method.
    Type: Application
    Filed: March 10, 2015
    Publication date: September 17, 2015
    Inventors: Yangyang Xu, Ioannis Akrotirianakis, Amit Chakraborty
  • Publication number: 20150142384
    Abstract: A method for monitoring a condition of a system or process includes acquiring sensor data from a plurality of sensors disposed within the system (S41 and S44). The acquired sensor data is streamed in real-time to a computer system (S42 and S44). A discriminative framework is applied to the streaming sensor data using the computer system (S43 and S45). The discriminative framework provides a probability value representing a probability that the sensor data is indicative of an anomaly within the system. The discriminative framework is an integration of a Kalman filter with a logistical function (S41).
    Type: Application
    Filed: June 11, 2013
    Publication date: May 21, 2015
    Inventors: Yuan Chao, Amit Chakraborty, Holger Hackstein, Leif Wiebking
  • Publication number: 20150134120
    Abstract: A method of real-time optimization for a Combined Cooling, Heating and Power system, including determining a first operation sequence of a plurality of chillers and at least one thermal energy storage tank in the system over a time period (410) and determining a second operation sequence of the plurality of chillers and at least one thermal energy storage tank in the system over the time period by using the first operation sequence as input to a greedy algorithm (420).
    Type: Application
    Filed: March 7, 2013
    Publication date: May 14, 2015
    Inventors: Yu Sun, Amit Chakraborty
  • Patent number: 9020874
    Abstract: In a support vector regression approach to forecasting power load in an electrical grid, a feature learning scheme weights each feature in the input data with its correlation with the predicted load, increasing the prediction accuracy. The kernel matrix for the input training data is computed such that features that align better with the target variable are given greater weight. The resulting load forecast may be used to compute commands sent to demand response modules.
    Type: Grant
    Filed: October 26, 2012
    Date of Patent: April 28, 2015
    Assignee: Siemens Aktiengesellschaft
    Inventors: Kai Zhang, Fabian Moerchen, Amit Chakraborty
  • Patent number: 9009074
    Abstract: Systems and methods are provided for generating and publishing electronic spare parts catalogs that support electronic business processes for managing and selling spare parts for complex machines and systems, such as gas turbines. Automated systems and methods for generating electronic catalogs of spare parts employ an extensible, template-based framework to extract and integrate catalog content (static and/or real-time spare parts data) from various backend business information systems and data sources.
    Type: Grant
    Filed: August 31, 2005
    Date of Patent: April 14, 2015
    Assignees: Siemens Aktiengesellschaft, Siemens Corporation
    Inventors: Amit Chakraborty, Liang H. Hsu, Zhijing Liu, Jan Eggebrecht
  • Patent number: 8983811
    Abstract: Methods are disclosed that teach two simulators used with demand response management systems. The first simulator generates load patterns from historical customer consumption data and generates customer loads from the generated load patterns. The second simulator generates customer response to changing electricity prices using an econometric characterization of the customer response.
    Type: Grant
    Filed: October 31, 2012
    Date of Patent: March 17, 2015
    Assignee: Siemens Aktiengesellschaft
    Inventors: Tolga Han Seyhan, Amit Chakraborty
  • Patent number: 8977524
    Abstract: A method for approximating an optimal power flow of a smart electric power grid includes providing a cost function that models a smart electric power grid having buses connected by branches, deriving a set of linear equations that minimize the cost function subject to constraints from an expression of an extremum of the cost function with respect to all arguments, reducing a dimension of the linear equations by solving for a subset of the linear equations, re-organizing the reduced dimension linear equations into primal and dual parts, and decomposing the re-organized reduced dimensional linear equations into two systems of block matrix equations which can be solved by a series of back substitutions. A solution of the two systems of block matrix equations yields conditions for a lowest cost per kilowatthour delivered through the smart electric power grid.
    Type: Grant
    Filed: March 6, 2012
    Date of Patent: March 10, 2015
    Assignee: Siemens Aktiengesellschaft
    Inventors: Motto Alexis Legbedji, Ruken Duzgun, Ioannis Akrotirianakis, Amit Chakraborty
  • Publication number: 20150019181
    Abstract: NOx generation in a coal burning furnace is estimating using a chemical reactor network model. The model is constructed with ideal chemical reactor modules, an input matrix and a tunable parameter matrix defining split ratios and flow rates among the ideal chemical reactor modules. Values in the tunable parameter matrix are learned by first measuring actual furnace outputs of the coal burning furnace for a known set of actual furnace inputs, and then applying the chemical reactor network, including an initially populated tunable parameter matrix, to a populated input matrix representing the known set of actual furnace inputs. The actual furnace outputs are compared with the output matrix, and the tunable parameter matrix is adjusted based on the comparison.
    Type: Application
    Filed: July 8, 2014
    Publication date: January 15, 2015
    Inventors: Lu Wang, Zhixuan Duan, Chao Yuan, Yu Sun, Amit Chakraborty
  • Patent number: 8886574
    Abstract: A generalized pattern recognition is used to identify faults in machine condition monitoring. Pattern clusters are identified in operating data. A classifier is trained using the pattern clusters in addition to annotated training data. The operating data is also used to cluster the signals in the operating data into signal clusters. Monitored data samples are then classified by evaluating confidence vectors that include substitutions of signals contained in the training data by signals in the same signal clusters as the signals contained in the training data.
    Type: Grant
    Filed: June 12, 2012
    Date of Patent: November 11, 2014
    Assignee: Siemens Aktiengesellschaft
    Inventors: Chao Yuan, Amit Chakraborty, Leif Wiebking, Holger Hackstein
  • Publication number: 20140229012
    Abstract: A method to manage operating costs of a combined cooling heating and power (CCHP) plant that includes converting complex models of underlying components of the plant into simplified models (S101), performing an optimization that uses the simplified models as constraints of the optimization to output at least one decision variable (S102), and adjusting controls of the plant based on one or more of the output decision variables (S103).
    Type: Application
    Filed: August 17, 2012
    Publication date: August 14, 2014
    Applicant: Siemens Aktiengesellschaft
    Inventors: Vikas Chandan, Ioannis Akrotirianakis, Amit Chakraborty
  • Patent number: 8719194
    Abstract: A method for training a classifier for selecting features in sparse data sets with high feature dimensionality includes providing a set of data items x and labels y, minimizing a functional of the data items x and associated labels y L ? ( w , b , a , c , ? 1 , ? 2 ) := 1 N ? ? i = 1 N ? a i + ? 1 ? ? c ? 1 + ? 2 2 ? ? w ? 2 2 + ? 1 T ? ( e - Y ? ( Xw + be ) - a ) + ? 2 T ? ( w - c ) + ? 1 2 ? ? e - Y ? ( Xw + be ) - a ? 2 2 + ? 2 2 ? ? w - c ? 2 2 to solve for hyperplane w and offset b of a classifier by successively iteratively approximating w and b, auxiliary variables a and c, and multiplier vectors ?1 and ?2, wherein ?1, ?2, ?1, and ?2 are predetermined constants, e is a unit vector, and X and Y are respective matrix representations of the data items x and labels y; providing non-zero elements of the hyperplane vector w and corresponding components of X and Y as arguments to an interior point method solv
    Type: Grant
    Filed: September 12, 2012
    Date of Patent: May 6, 2014
    Assignee: Siemens Aktiengesellschaft
    Inventors: Zhiwei Qin, Xiaocheng Tang, Ioannis Akrotirianakis, Amit Chakraborty
  • Publication number: 20140032187
    Abstract: A method of approximating a solution of a stochastic state estimation (SSE) model of an electric grid, includes choosing (70) starting anchor points in an SSE model of an electric grid, relaxing (71) constraints of an SSE objective function to solve for a feasible solution of the SSE model, calculating (72) updated dual variables and infeasibility reduction directions from the feasible solution, generating (73) a linear cut for the chosen starting anchor points, choosing (74) a step size toward the reduction directions, and updating (75) the anchor points through branching by making the chosen step, wherein each anchor point defines a rectangle that at least partially covers a feasible solution set of the SSE model and the set of rectangles covering the feasible solution set of the SSE model define an approximate solution of the SSE model of said electric grid.
    Type: Application
    Filed: November 4, 2011
    Publication date: January 30, 2014
    Applicant: SIEMENS CORPORATION
    Inventors: Motto Alexis Legbedji, Andrey Torzhkov, Amit Chakraborty
  • Publication number: 20130332773
    Abstract: A generalized pattern recognition is used to identify faults in machine condition monitoring. Pattern clusters are identified in operating data. A classifier is trained using the pattern clusters in addition to annotated training data. The operating data is also used to cluster the signals in the operating data into signal clusters. Monitored data samples are then classified by evaluating confidence vectors that include substitutions of signals contained in the training data by signals in the same signal clusters as the signals contained in the training data.
    Type: Application
    Filed: June 12, 2012
    Publication date: December 12, 2013
    Applicants: Siemens Aktiengesellschaft, Siemens Corporation
    Inventors: Chao Yuan, Amit Chakraborty, Leif Wiebking, Holger Hackstein
  • Publication number: 20130238148
    Abstract: A method for approximating an optimal power flow of a smart electric power grid includes providing a cost function that models a smart electric power grid having buses connected by branches, deriving a set of linear equations that minimize the cost function subject to constraints from an expression of an extremum of the cost function with respect to all arguments, reducing a dimension of the linear equations by solving for a subset of the linear equations, re-organizing the reduced dimension linear equations into primal and dual parts, and decomposing the re-organized reduced dimensional linear equations into two systems of block matrix equations which can be solved by a series of back substitutions. A solution of the two systems of block matrix equations yields conditions for a lowest cost per kilowatthour delivered through the smart electric power grid.
    Type: Application
    Filed: March 6, 2012
    Publication date: September 12, 2013
    Applicant: Siemens Corporation
    Inventors: Motto Alexis Legbedji, Ruken Duzgun, Ioannis Akrotirianakis, Amit Chakraborty
  • Publication number: 20130238294
    Abstract: According to an aspect of the invention, there is provided a method for optimizing a cost of electric power generation in a smart site energy management model, including providing a cost function that models a smart building-grid energy system of a plurality of buildings on a site interconnected with electric power grid energy resources and constraints due to a building model, an electric grid model, and a building-grid interface model, where decision variables for each of the building model, the electric grid model, and the building-grid interface model are box-constrained, and minimizing the cost function subject to the building model constraints, the electric grid model constraints, and building-grid interface model constraints.
    Type: Application
    Filed: February 6, 2013
    Publication date: September 12, 2013
    Applicant: Siemens Corporation
    Inventors: Motto Alexis Legbedji, Yu Sun, Amit Chakraborty
  • Publication number: 20130144575
    Abstract: Methods are disclosed that teach two simulators used with demand response management systems. The first simulator generates load patterns from historical customer consumption data and generates customer loads from the generated load patterns. The second simulator generates customer response to changing electricity prices using an econometric characterization of the customer response.
    Type: Application
    Filed: October 31, 2012
    Publication date: June 6, 2013
    Inventors: Tolga Han Seyhan, Amit Chakraborty
  • Publication number: 20130073489
    Abstract: A method for training a classifier for selecting features in sparse data sets with high feature dimensionality includes providing a set of data items x and labels y, minimizing a functional of the data items x and associated labels y L ? ( w , b , a , c , ? 1 , ? 2 ) := 1 N ? ? i = 1 N ? a i + ? 1 ? ? c ? 1 + ? 2 2 ? ? w ? 2 2 + ? 1 T ? ( e - Y ? ( Xw + be ) - a ) + ? 2 T ? ( w - c ) + ? 1 2 ? ? e - Y ? ( Xw + be ) - a ? 2 2 + ? 2 2 ? ? w - c ? 2 2 to solve for hyperplane w and offset b of a classifier by successively iteratively approximating w and b, auxiliary variables a and c, and multiplier vectors ?1 and ?2, wherein ?1, ?2, ?1, and ?2 are predetermined constants, e is a unit vector, and X and Y are respective matrix representations of the data items x and labels y; providing non-zero elements of the hyperplane vector w and corresponding components of X and Y as arguments to an interior point method solv
    Type: Application
    Filed: September 12, 2012
    Publication date: March 21, 2013
    Applicant: Siemens Corporation
    Inventors: Zhiwei Qin, Xiaocheng Tang, Ioannis Akrotirianakis, Amit Chakraborty
  • Patent number: 8396572
    Abstract: A method for optimizing operational settings for a plurality of energy devices includes representing each of the plurality of energy devices in terms of a set of decision variables and operational parameters. The decision variables and operational parameters are constrained based on operational conditions and interrelationship within the plurality of energy devices. A two-tiered model of the plurality of energy devices is generated wherein a top tier of the model represents interaction of various sub-models and a bottom tier of the model includes a set of the sub-models that form the top tier, each sub-model representing detailed operation of the plurality of energy devices. The two-tiered model is optimized to provide either a schedule of operation for the plurality of energy devices or real-time control for the plurality of energy devices.
    Type: Grant
    Filed: January 22, 2010
    Date of Patent: March 12, 2013
    Assignee: Siemens Corporation
    Inventors: Andrey Torzhkov, Amit Chakraborty
  • Publication number: 20130035885
    Abstract: A statistical technique is used to estimate the status of switching devices (such as circuit breakers, isolator switches and fuses) in distribution networks, using scares (i.e., limited or non-redundant) measurements. Using expected values of power consumption, and their variance, the confidence level of identifying the correct topology, or the current status of switching devices, is calculated using any given configuration of real time measurements. Different topologies are then compared in order to select the most likely topology at the prevailing time. The measurements are assumed as normally distributed random variables, and the maximum likelihood principle or a support vector machine is applied.
    Type: Application
    Filed: July 26, 2012
    Publication date: February 7, 2013
    Applicants: Massachusetts Institute of Technology, Siemens Corporation
    Inventors: Yoav Sharon, Anuradha Annaswamy, Motto Alexis Legbedji, Amit Chakraborty