Abstract: Methods and apparatus for managing circular queues are disclosed. A pointer designates an index position of a particular queue element and contains an additional pointer state, whereby two pointer values (split indexes) can designate the same index position. Front and rear pointers are respectively managed by dequeue and enqueue logic. The front pointer state and rear pointer state distinguish full and empty queue states when both pointers designate the same index position. Asynchronous dequeue and enqueue operations are supported, no lock is required, and no queue entry is wasted. Hardware and software embodiments for numerous applications are disclosed.

Abstract: Methods and systems for out-of-distribution (OOD) detection in autonomous driving systems are described. A method for use in an autonomous driving system may include filtering feature vectors. The feature vectors may be filtered using a first filter to obtain clusters of feature vectors. The method may include assigning one or more images to a respective cluster based on a feature vector of the image. The method may include filtering a subset of the images using a second filter to determine a classification model. The method may include storing the classification model on a vehicle control system of a vehicle. The method may include detecting an image using a vehicle sensor. The method may include classifying the detected image based on the classification model. The method may include performing a vehicle action based on the classified detected image.

Abstract: The present disclosure disclose method and apparatus for determining memory requirement for processing a DNN model on a device, a method includes receiving a DNN model for an input, wherein the DNN model includes a plurality of processing layers. The method includes generating a network graph of the DNN model. The method includes creating a colored network graph of the DNN model based on the identified execution order of the plurality of processing layers. The colored network graph indicates assignment of at least one memory buffer for storing at least one output of at least one processing layer. The method includes determining at least one buffer reuse overlap possibility across the plurality of processing layers. Based on the determined at least one buffer reuse overlap possibility, the method includes determining and assigning the memory required for processing the DNN model.

Abstract: Apparatus and methods are disclosed for scheduling tasks in a heterogeneous computing environment. Coarse scheduling of a received task-set is performed centrally, with tasks dispatched to respective processing resources including one or more accelerators. At each accelerator, sub-tasks of a received task are identified, scheduled, and executed. Data-transfer and computation sub-tasks can be pipelined. The accelerator operates using small tiles of local data, which are transferred to or from a large shared reservoir of main memory. Sub-task scheduling can be customized to each accelerator; coarse task scheduling can work on larger tasks; both can be efficient. Simulations demonstrate large improvements in makespan and/or circuit area. Disclosed technologies are scalable and can be implemented in varying combinations of hard-wired or software modules. These technologies are widely applicable to high-performance computing, image classification, media processing, wireless coding, encryption, and other fields.

Abstract: Methods and apparatus for managing circular queues are disclosed. A pointer designates an index position of a particular queue element and contains an additional pointer state, whereby two pointer values (split indexes) can designate the same index position. Front and rear pointers are respectively managed by dequeue and enqueue logic. The front pointer state and rear pointer state distinguish full and empty queue states when both pointers designate the same index position. Asynchronous dequeue and enqueue operations are supported, no lock is required, no queue entry is wasted. Hardware and software embodiments for numerous applications are disclosed.

Abstract: Methods and systems for out-of-distribution (OOD) detection in autonomous driving systems are described. A method for use in an autonomous driving system may include filtering feature vectors. The feature vectors may be filtered using a first filter to obtain clusters of feature vectors. The method may include assigning one or more images to a respective cluster based on a feature vector of the image. The method may include filtering a subset of the images using a second filter to determine a classification model. The method may include storing the classification model on a vehicle control system of a vehicle. The method may include detecting an image using a vehicle sensor. The method may include classifying the detected image based on the classification model. The method may include performing a vehicle action based on the classified detected image.

Abstract: The method of producing lithium titanate anode material for lithium ion battery applications is comprising of: a) mixing of mixed phase having 60-80% anatase and 20-40% rutile of TiO2 as titanium precursor with Li2CO3 as lithium precursor in a stoichiometric ratio of 5:4 and adding with 2 to 5% stearic acid as process control agent as well as carbon precursor; b) milling in horizontal attrition milling unit maintained with the ball to powder ratio of 10:1-12:1 at 250-500 rpm for 0.5 to 2 hrs c) repeating the milling for 40 to 48 times; d) palletisation of the milled powder to a diameter of 30-35 mm under a pressure of 0.5-1 ton; e) annealing under inert atmosphere at a temperature of 700-900° C. for a period of 2-12 hrs; and f) grinding the resultant annealed composite powder to a fine powder. Resultant powder has shown excellent electrochemical properties in terms of charge-discharge, cyclic-stability and rate capability.

Abstract: A method for diagnosing a waste gate valve malfunction in a power generation system is presented. The method includes determining an actual pressure differential across a throttle valve. The method further includes determining an estimated pressure differential across the throttle valve based on one or more first operating parameters of the power generation system. Furthermore, the method includes determining an absolute difference between the actual pressure differential and the estimated pressure differential. Moreover, the method also includes comparing the absolute difference with a threshold value and if the absolute difference is greater than the threshold value, determining an operating condition of the throttle valve. Additionally, the method includes determining whether the waste gate valve has malfunctioned based on the determined operating condition of the throttle valve. An engine controller and a power generation system employing the method are also presented.

Abstract: A tangible, non-transitory computer readable medium includes computer instructions stored thereon, the computer instructions, when executed by a processor, cause the processor to retrieve model inputs indicative of mechanical systems data, economic data, contractual data, regulatory data, or any combination thereof, associated with at least one compression system. Furthermore, the instructions cause the processor to retrieve a model that derives an operation schedule for the at least one compression system based on the model inputs. Then the instructions cause the processor to derive an operation schedule for the at least one compression system based on the model inputs and the model, and apply the operation schedule to the at least one gas compression system.

Abstract: The present disclosure disclose method and apparatus for determining memory requirement for processing a DNN model on a device, a method includes receiving a DNN model for an input, wherein the DNN model includes a plurality of processing layers. The method includes generating a network graph of the DNN model. The method includes creating a colored network graph of the DNN model based on the identified execution order of the plurality of processing layers. The colored network graph indicates assignment of at least one memory buffer for storing at least one output of at least one processing layer. The method includes determining at least one buffer reuse overlap possibility across the plurality of processing layers. Based on the determined at least one buffer reuse overlap possibility, the method includes determining and assigning the memory required for processing the DNN model.

Abstract: A method for diagnosing a waste gate valve malfunction in a power generation system is presented. The method includes determining an actual pressure differential across a throttle valve. The method further includes determining an estimated pressure differential across the throttle valve based on one or more first operating parameters of the power generation system. Furthermore, the method includes determining an absolute difference between the actual pressure differential and the estimated pressure differential. Moreover, the method also includes comparing the absolute difference with a threshold value and if the absolute difference is greater than the threshold value, determining an operating condition of the throttle valve. Additionally, the method includes determining whether the waste gate valve has malfunctioned based on the determined operating condition of the throttle valve. An engine controller and a power generation system employing the method are also presented.

Abstract: The present application provides an aftertreatment system for treating an exhaust stream of an engine. The aftertreatment system may include a selective catalyst reduction system positioned downstream of the engine, a secondary catalyst positioned downstream of the selective catalyst reduction system, a first gas sensor positioned between the engine and the selective catalyst reduction system, a second gas sensor positioned between the selective catalyst reduction system and the secondary catalyst, and a third gas sensor positioned downstream of the secondary catalyst.

Abstract: The present application provides an aftertreatment system for treating an exhaust stream of an engine. The aftertreatment system may include a selective catalyst reduction system positioned downstream of the engine, a secondary catalyst positioned downstream of the selective catalyst reduction system, a first gas sensor positioned between the engine and the selective catalyst reduction system, a second gas sensor positioned between the selective catalyst reduction system and the secondary catalyst, and a third gas sensor positioned downstream of the secondary catalyst.

Abstract: The method of producing lithium titanate anode material for lithium ion battery applications is comprising of: a) mixing of mixed phase having 60-80% anatase and 20-40% rutile of TiO2 as titanium precursor with Li2CO3 as lithium precursor in a stoichiometric ratio of 5:4 and adding with 2 to 5% stearic acid as process control agent as well as carbon precursor; b) milling in horizontal attrition milling unit maintained with the ball to powder ratio of 10:1-12:1 at 250-500 rpm for 0.5 to 2 hrs c) repeating the milling for 40 to 48 times; d) palletisation of the milled powder to a diameter of 30-35 mm under a pressure of 0.5-1 ton; e) annealing under inert atmosphere at a temperature of 700-900° C. for a period of 2-12 hrs; and f) grinding the resultant annealed composite powder to a fine powder. Resultant powder has shown excellent electrochemical properties in terms of charge-discharge, cyclic-stability and rate capability.

Abstract: A method for diagnosing a waste gate valve malfunction in a power generation system is presented. The method includes determining an actual pressure differential across a throttle valve. The method further includes determining an estimated pressure differential across the throttle valve based on one or more first operating parameters of the power generation system. Furthermore, the method includes determining an absolute difference between the actual pressure differential and the estimated pressure differential. Moreover, the method also includes comparing the absolute difference with a threshold value and if the absolute difference is greater than the threshold value, determining an operating condition of the throttle valve. Additionally, the method includes determining whether the waste gate valve has malfunctioned based on the determined operating condition of the throttle valve. An engine controller and a power generation system employing the method are also presented.

Abstract: A system includes an aftertreatment system configured to treat emissions from an engine via a catalyst and a controller. The controller is configured to obtain one or more engine signals representative of operations of the engine and to execute a model to derive an estimated catalyst emission based on the one or more engine signals and on an expected catalyst degradation. The controller is further configured to obtain one or more catalyst signals representative of catalyst performance, and to generate an adaptation signal configured to improve accuracy of the model based on the one or more catalyst signals. The controller is also configured to apply the adaptation signal and the estimated catalyst emission to generate an engine control signal.

Abstract: A system includes an aftertreatment system configured to treat emissions from an engine via a catalyst and a controller. The controller is configured to obtain one or more engine signals representative of operations of the engine and to execute a model to derive an estimated catalyst emission based on the one or more engine signals and on an expected catalyst degradation. The controller is further configured to obtain one or more catalyst signals representative of catalyst performance, and to generate an adaptation signal configured to improve accuracy of the model based on the one or more catalyst signals. The controller is also configured to apply the adaptation signal and the estimated catalyst emission to generate a urea injection control signal.

Abstract: A tangible, non-transitory computer readable medium includes computer instructions stored thereon, the computer instructions, when executed by a processor, cause the processor to retrieve model inputs indicative of mechanical systems data, economic data, contractual data, regulatory data, or any combination thereof, associated with at least one compression system. Furthermore, the instructions cause the processor to retrieve a model that derives an operation schedule for the at least one compression system based on the model inputs. Then the instructions cause the processor to derive an operation schedule for the at least one compression system based on the model inputs and the model, and apply the operation schedule to the at least one gas compression system.

Abstract: A system includes a hybrid power plant controller programmed to receive a plurality of signals representative of one or more operating parameters of a hybrid power plant. The hybrid power plant includes at least one gas turbine engine, at least one gas engine, and at least one catalyst system. The hybrid power plant controller is programmed to utilize closed-loop optimal control to generate one or more operational setpoints based on the one or more operating parameters for the hybrid power plant to optimize performance of the hybrid power plant. The hybrid power plant controller uses closed-loop optimal control to provide the one or more operational setpoints to respective controllers of the at least one gas turbine engine, the at least one gas engine, and the at least one catalyst system to control operation of the gas turbine engine, the gas engine, and the catalyst system.

Abstract: In one embodiment, a system may include a gas turbine system. the gas turbine system includes a gas turbine, an after-treatment system that may receive exhaust gases from the gas turbine system, and a controller that may receive inputs and model operational behavior of an industrial plant based on the inputs. The industrial plant may include the gas turbine and the after-treatment system. The controller may also determine one or more operational parameter setpoints for the industrial plant, select the one or more operational parameter setpoints that reduce an output of a cost function, and apply the one or more operational parameter setpoints to control the industrial plant.