Integration of physical sensors in a data assimilation framework

Abstract

A method and system for outputting a state of a physical system using a calibrated model of the physical system, wherein the calibrated model is used to generate a model prediction. The system includes a plurality of sensors connected to a routing node for monitoring measurement data of the physical system. A first sensor of the plurality of sensors includes a logic module configured to determine an uncertainty quantification and combine the uncertainty quantification with the model prediction to output the state of the physical system.

Description

Technical Field

[0001] The present invention relates to computer modeling, and more particularly to state modeling of complex physical systems. Background Art

[0002] Data assimilation is a technique that combines observational data with the output of a numerical model to estimate the state of a system. A data assimilation network can include sensors that observe various aspects of a physical system (e.g., ocean currents). Sensors can be incorporated into the model state of a numerical model of the physical system. Sensors can perform measurements, basic data processing, and communication. The model state is a representation of variables that attempt to fully describe the actual physical state of the system. The model is used because the number of available observations can be an order of magnitude less than the number of values ​​required to specify the state of the physical system. Physical sensors of current technology have capabilities that typically include the following: measurement, basic data processing, and communication. However, a lot of effort is required to integrate noisy and redundant sensor observations with prediction systems for monitoring and managing complex physical systems (e.g., fluid systems, such as lakes).

[0003] Therefore, there is a need in the art to solve the above problems. Summary of the invention

[0004] From another aspect, the present invention provides a method for evaluating the state of a physical system, the method comprising: using a calibrated model of the physical system to generate model predictions; and using multiple sensors connected to a routing node to monitor measurement data of the physical system, wherein a first sensor of the multiple sensors includes a logic module configured to determine uncertainty quantification, and combine the uncertainty quantification with the model predictions to output the state of the physical system.

[0005] From another aspect, the present invention provides a system comprising: a calibrated model of a physical system, configured to generate model predictions; and a plurality of sensors that monitor measurement data of the physical system and are connected to a routing node, wherein a first sensor of the plurality of sensors comprises a logic module configured to determine an uncertainty quantification and combine the uncertainty quantification with the model predictions to output a state of the physical system.

[0006] Viewed from another aspect, the present invention provides a computer program product for evaluating the state of a physical system, the computer program product comprising a computer-readable storage medium which can be read by a processing circuit and stores instructions which are executed by the processing circuit to execute a method for performing the steps of the present invention.

[0007] Viewed from another aspect, the invention provides a computer program stored on a computer readable medium and loadable into the internal memory of a digital computer, comprising software code portions for performing the steps of the invention when said program is run on a computer.

[0008] A computer program product for assessing a state of a physical system, the computer program product comprising: a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to: generate model predictions using a calibrated model of the physical system; and monitor measurement data of the physical system using a plurality of sensors connected to a routing node, wherein a first sensor of the plurality of sensors comprises a logic module configured to determine an uncertainty quantification, and combine the uncertainty quantification with the model prediction to output the state of the physical system.

[0009] According to one embodiment of the present invention, a method for evaluating the state of a physical system includes generating model predictions using a calibrated model of the physical system, and monitoring measurement data of the physical system using multiple sensors connected to a routing node, wherein a first sensor of the multiple sensors includes a logic module configured to determine an uncertainty quantification about the measurement data, and combine the uncertainty quantification with the model prediction to output the state of the physical system.

[0010] According to another embodiment, a system includes a calibrated model of a physical system configured to generate model predictions, and a plurality of sensors that monitor measurement data of the physical system and are connected to routing nodes, wherein a first sensor of the plurality of sensors includes a logic module configured to determine an uncertainty quantification and combine the uncertainty quantification with the model predictions to output a state of the physical system.

[0011] According to another embodiment, a computer program product for evaluating a state of a physical system comprises a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code being executable by one or more computer processors to generate model predictions using a calibrated model of the physical system, and to monitor measurement data of the physical system using a plurality of sensors connected to a routing node, wherein a first sensor of the plurality of sensors comprises a logic module configured to determine an uncertainty quantification, and to combine the uncertainty quantification with the model prediction to output the state of the physical system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The present invention will now be described, by way of example only, with reference to preferred embodiments, as shown in the following drawings:

[0013] Figure 1 is a block diagram of another embodiment of a computing system configured to monitor, model, and help determine the state of a physical system;

[0014] Figure 2 is a block diagram of another embodiment of a computing system configured to monitor and facilitate determining a state of a physical system at a sensor level;

[0015] Figure 3 is a flow chart of an embodiment of a method of performing aspects of data assimilation to model the state of a complex physical system using a sensor network process;

[0016] Figure 4 is a flow chart of an embodiment of a method of performing aspects of data assimilation to model the state of a complex physical system using local data assimilation analysis;

[0017] Figure 5 is a flow chart of an embodiment of a method of performing aspects of data assimilation to model the state of a complex physical system using core data assimilation analysis;

[0018] Figure 6 shows a block diagram of a computing system according to an embodiment; and

[0019] Figure 7 Further shown is a server according to one embodiment, such as Figure 6 server. DETAILED DESCRIPTION

[0020] Embodiments of the system may use data assimilation to optimally combine available observations with numerical models in order to perform predictive analysis of the system. The system may integrate sensors within a predictive data assimilation framework by enabling sensors with advanced capabilities. Embodiments of the system may automatically integrate noisy and redundant sensor observations with predictive systems for monitoring and managing complex physical systems, such as fluid systems in lakes.

[0021] A related method can output a state of a physical system using a calibrated model of the physical system. The calibrated model can be used to generate a model prediction. The system includes a plurality of sensors connected to a routing node for monitoring measurement data of the physical system. A first sensor of the plurality of sensors includes a logic module configured to determine an uncertainty quantification and combine the uncertainty quantification with the model prediction to output a state of the physical system.

[0022] Unlike traditional data assimilation, the system may include combining local and edge (on-sensor) analysis to produce a better data assimilation method. Edge analysis may be used to estimate sensor uncertainty and the weights attached to measurements relative to model estimates.

[0023] Certain embodiments of the system can bridge the gap between pure data collection by sensors and online predictive modeling. Predictive modeling can be oriented toward decision support in the management of complex physical systems. The system can include integrated sensors and predictive models within a data assimilation framework.

[0024] Embodiments of the system can use knowledge of the raw sensor data and the data filtering process to estimate uncertainty in the measurement data with high accuracy in real time. The system can identify sensors and parameters that can be modified in the raw data filtering process based on the accuracy of the corrected model predictions. The system's auto-calibration mechanism can use feedback from the data assimilation framework at the core analysis level to optimize the type and parameters of the data filtering process at the sensor level.

[0025] Embodiments of the system can model the state of a complex physical system (e.g., a hurricane, a lake system, or a forested area). The system can use calibrated coupled models of the physical system (e.g., weather, fluid dynamics, and / or runoff models). The system can include a sensor network, local data assimilation analysis, and core data assimilation analysis.

[0026] The sensor network of an embodiment may include multiple sensors connected to the system through one or more routing nodes. The sensors may be configured to perform data acquisition, streaming data filtering, and transmission of data to the cloud or central data warehouse. It is noteworthy that the sensors may be additionally configured to perform uncertainty quantification and may report in real time. The sensors may perform acquisition of feedback from local and core data assimilation analysis. The sensors may also use system feedback to perform automatic type selection and parameter setting of filtering mechanisms. The sensors may use a wide range of streaming data filter types.

[0027] Local data assimilation analysis can include components of the edge architecture, such as gateways, messaging interfaces, and sensor data storage. Notably, data assimilation analysis can be responsible for optimizing and otherwise adjusting the filtering process at the sensor level.

[0028] The core data assimilation analysis can include sensor observations that can be assimilated. For example, sensor observations can be combined with model predictions using information about sensor-level uncertainty. Uncertainty estimates can be used dynamically based on the results of model performance or after the data assimilation analysis.

[0029] Parameters at the sensor level can be related to the streaming data filtering process. Parameters at the core data analysis level can be related to the covariance calculation used in assimilating available measurements. A heuristic process can be used to adjust parameters at both levels.

[0030] The system may include a calibrated coupled model associated with a physical system (e.g., fluid dynamics, runoff, weather), and a plurality of sensors connected to the physical system via a routing node. A first sensor of the plurality of sensors may be configured to determine an uncertainty quantification. The uncertainty quantification may be reported in real time. The system may combine sensor observations with model predictions using information about sensor-level uncertainty.

[0031] Embodiments of the system may enable advanced analytical capabilities at the sensor level to intelligently integrate physical sensing, modeling, and data assimilation. The system may perform observation processing on the sensor side in synchronization with data processing at the data assimilation framework. Data processing may include processes beyond simple filtering of sensor measurements. For example, data processing at the sensor may include simultaneous filtering and data assimilation. The system may enable quality control on the sensor side guided by the data assimilation framework. One or more sensors may be configured to perform diagnostics of signal quality. Embodiments of the sensor may perform measurement noise characterization and adaptive sensor polling based on feedback from the data assimilation framework. The sensor may also provide diagnostics for improved sensor mesh networks.

[0032] Data filtering may include processing data at the sensor level for the purpose of reducing noise. An illustrative embodiment of data filtering may include using a low pass filter.

[0033] Data assimilation can include a process in which observations from sensors of a physical system are used to correct predictions of a numerical model of the physical system of interest. Local sensor data assimilation analysis can include analysis at the sensor (e.g., edge or gateway) level to optimize the raw data stream filtering process by adjusting parameters using feedback on prediction accuracy from the core data assimilation analysis level.

[0034] The edge gateway may include components that can not only manipulate sensor data traffic, but also store data and take actions on the data. The actions of the embodiments may be performed by local data assimilation analysis. The core data assimilation analysis may combine sensor data and metadata with model predictions to improve model results. The core data assimilation analysis may also improve the data assimilation process using real-time filtered sensor data plus information about uncertainty in real-time filtered sensor data.

[0035] In one particular implementation, the data assimilation system may include a network of sensor probes deployed throughout a lake. The sensor probes may be integrated with local and core analytics. Each probe of this embodiment acquires data about several environmental parameters frequently and at a constant rate. The resulting data stream may be filtered at the probe level to reduce noise. The probe sensors may provide accurate measurements and information about the uncertainty of the probe sensor data in real time. The data assimilation system may adjust the filtering process to obtain the best possible information at the sensor level in order to assimilate the data and data uncertainty to improve model predictions.

[0036] Continuing with the above example, for a given variable (e.g., temperature), a sensor may collect a raw data stream at a high sampling frequency (e.g., 4 Hz). The raw data measurements may be relatively noisy due to local environmental conditions. The sensor may be equipped with a filter bank to pre-process the raw data.

[0037] The filtered data points (e.g., the output of a moving average filter) may include associated times and time intervals. The filter may have parameters including the length of a rolling window. The uncertainty of the reported measurements may be estimated during the filtering process. Any other type of filter (e.g., an adaptive filter) and filter parameters may produce different preprocessing pairs.

[0038] This feature is in contrast to conventional sensors, which neither report such uncertainties nor receive feedback to select different filters (and their parameters). Uncertainties can be significantly affected by filter parameters and change over time. Feedback from core data assimilation analysis can be used to continuously tune parameters.

[0039] The field measurements can be mapped to a physical model of the lake with a predefined spatiotemporal resolution. Data assimilation in this example can include the use of an optimal interpolation scheme:

[0040] The calculation and update may include measurement covariance matrices for measurements and models. The calculation process may use real-time uncertainty estimates. The assimilation process may include optimally combining data and data uncertainty, model predictions, modeling uncertainty, and covariance estimates. The output of the data assimilation analysis may be evaluated in terms of improving model accuracy.

[0041] The optimization process of an embodiment of the system can adjust parameters at the core data assimilation level by adjusting parameters (e.g., measurement uncertainty) of the state error covariance calculation. Another or the same embodiment can change parameters at the local data assimilation level by providing feedback to adjust data filtering parameters. The modeling system can use data assimilation to optimally combine available observations with numerical models in order to perform predictive analysis of physical systems. The associated method can use a calibrated model of the physical system to output the state of the physical system, wherein the calibrated model is used to generate model predictions. The system includes a plurality of sensors connected to a routing node for monitoring measurement data of the physical system. The system can integrate the sensors within a predictive data assimilation framework by giving the sensors advanced capabilities. At least one of the sensors includes a logic module configured to determine uncertainty quantification about the measurement data, and combine the uncertainty quantification with the model prediction to output the state of the physical system. An embodiment of the system can automatically integrate noisy and redundant sensor observations with a prediction system for monitoring and managing complex physical systems.

[0042] Figure 1 1 is a block diagram of an embodiment of a system 100 configured to model the state of a complex physical system. The system may include a sensor network 102 including a plurality of sensors 108, a local data assimilation analysis 104, and a core data assimilation analysis 106 (represented by a dashed boundary line). The physical system may include natural forces, such as those present in the physical system, such as: geographic regions, water systems, gravity systems, thermal systems, and wind systems, among others.

[0043] The sensor network 102 of an embodiment may include multiple sensors 108 connected to the system 100 through one or more routing nodes 112. The sensors 108 may be configured to perform data acquisition, streaming data filtering, and transmitting data to a cloud or central data warehouse. The sensors 108 may additionally be configured to perform uncertainty quantification and may report results in real time. The sensors 108 may perform acquisition of feedback from local and core data assimilation analysis. The sensors 108 may also use system feedback to perform automatic type selection and parameter setting of filtering mechanisms. The sensors 108 may use a variety of streaming data filter types.

[0044] In operation, the sensor network 102 may execute a process that includes the physical sensors 108-111 acquiring environmental data at a constant rate. A filtering algorithm executed at the sensor 108 (or at a processor in communication with the sensor 108) may process the data stream to produce data stored in the sensor data storage device 118. The type of filtering algorithm and the parameters of the filtering may be automatically optimized at the core and local data assimilation analysis stages 104, 106, and may be set accordingly at the sensor level 102. The sensor 108 may monitor and provide feedback on measurement uncertainty (e.g., the accuracy of the measurement) based on the automatic analysis during the filtering process.

[0045] The local data assimilation analysis 104 may include components of the edge architecture, such as gateways, messaging interfaces, and sensor data storage devices. The data assimilation analysis 104 may be responsible for optimizing and otherwise adjusting the filtering process at the sensor level. Figure 1 As shown, the local data assimilation analysis 104 may include an edge gateway module 114 , a sensor message transceiving interface 116 , a sensor data storage device 118 , and a data assimilation analysis module 120 .

[0046] The filtered sensor data may be received at the edge gateway module 114 and combined with relevant metadata to provide filtered measurements, uncertainty characteristics, and information about the filtering process. The data may be routed to the data assimilation analysis module 120 via the sensor messaging interface 116. Local or edge analysis at the data assimilation analysis module 120 may optimize the filtering process by adjusting parameters using feedback from the prediction accuracy at the core data assimilation analysis stage.

[0047] The core data assimilation analysis 106 may include sensor observations that may be assimilated. For example, sensor observations may be combined with model predictions using information about sensor-level uncertainty. Uncertainty estimates may be used dynamically based on the results of model performance or after the data assimilation analysis.

[0048] Parameters at the sensor level can be related to the streaming data filtering process. Parameters at the core data analysis level can be related to the covariance calculation used in assimilating available measurements. A heuristic process can be used to adjust parameters at both levels.

[0049] like Figure 1 As shown in the embodiment of FIG. 1 , the core data assimilation analysis 106 may include an observation processing module 122 , a data assimilation module 124 , a physical model module 126 , a forcing and boundary condition module 128 , an improved model result module 130 , and a data assimilation optimization module 132 .

[0050] The physical model module 126 can model the state of a complex physical system (eg, a lake system). The system can use a calibrated coupled model of the physical system (eg, fluid dynamics, runoff, and / or weather models).

[0051] The data assimilation module 124 may receive historical and real-time sensor data from the sensor data storage device 118 of the local data assimilation analysis 104. The sensor data may be filtered and include an indication of its uncertainty. The data assimilation module 124 may additionally include model predictions. The model predictions may be provided by the physical model module 126 and the forcing and boundary condition module 128.

[0052] The observation processing module 122 may provide the filtered observations and information about observation errors to the data assimilation module 124. The data assimilation module 124 may provide data assimilation feedback to the observation processing module 122.

[0053] The data assimilation module 124 may provide the optimal combination of observations and model results to the physical model module 126. The physical model module 126 may provide the model results and information modeling errors back to the data assimilation module 124.

[0054] The data assimilation module 124 can combine sensor data and metadata with model predictions to improve model results. The data assimilation module 124 can optimize results by adjusting data assimilation parameters and by providing feedback (eg, provided at the sensor level) for adjusting the filtering / uncertainty estimation process.

[0055] Figure 2 is a block diagram of another embodiment of a computing system 200 configured to monitor and facilitate determining a state of a physical system. Figure 2 All or some of the modules shown in the system 200 may exist and execute at the sensor level including the sensor 202. Thus, the sensor 202 of the system 200 may be coupled to or otherwise communicate with the additional sensor 204, the core data assimilation analysis level 206, and the local data assimilation analysis level 208. For example, the sensor module 202 may be connected directly or via a plurality of nodes 210.

[0056] The sensor module 202 or sensor may include a processor 212, an interface 214, and a memory 216. Figure 2As shown in the embodiment of the system 200, the memory 216 may include stored and real-time environmental data 218, a filtering algorithm module 220, and parameters 222 for analysis. The memory 216 may additionally include data stream data 224, historical data 226, an uncertainty measurement module 228, an analysis module 230, a real-time feedback module 232, and a monitoring module 234. The system 200 may perform a process including physical sensors 202, 204 acquiring environmental data 218 at a constant rate. The filtering algorithm 218 executed at the sensor 202, 204 may process the data stream to generate data stored in the historical database 226. The type of filtering algorithm 218 and the parameters 222 of the filtering may be automatically optimized at the core and local data assimilation analysis levels 206, 208, and may be set accordingly at the sensor level. The sensor 202, 204 may monitor the measurement uncertainty and provide feedback on the measurement uncertainty based on the automatic analysis during the filtering process. Figure 3-Figure 5 is a flow chart illustrating an embodiment of a method 300, 400, 500 of performing aspects of data assimilation in a manner consistent with an embodiment of the system. The method may be performed by, for example, Figure 1 The illustrative system 100 is implemented to model the state of a complex physical system using sensor network processes, local data assimilation analysis, and core data assimilation analysis.

[0057] More specifically, turn to Figure 3 In the flow chart of the sensor network process, at 302, the sensor network 102 can perform a process including the physical sensors 108-111 acquiring environmental data at a constant rate. At 304, the filtering algorithm executed at the sensor 108-111 (or a processor in communication with the sensor 108-111) can process the data stream to generate data stored in the sensor data storage device 118.

[0058] At 306, the type of filtering algorithm and the parameters of filtering may be automatically optimized at the core and local data assimilation analysis stages 104, 106, and the type of filtering algorithm and the parameters of filtering may be set accordingly at the sensor level 102. At 308, the sensors 108-111 may monitor and provide feedback regarding measurement uncertainty (e.g., accuracy of the measurement) based on the automatic analysis during the filtering process.

[0059] More specifically, turn to Figure 4 In the sensor network process of an embodiment of the method 400 shown in FIG. 4 , at 402 , filtered sensor data may be received at an edge gateway module and, at 404 , combined with relevant metadata to provide filtered measurements, uncertainty characteristics, and information about the filtering process.

[0060] At 406, the data may be routed to the data assimilation analysis module 120 via the sensor messaging interface 116. Local or edge analysis at the data assimilation analysis module 120 may optimize the filtering process by adjusting parameters at 408 using feedback from the prediction accuracy of the core data assimilation analysis stage.

[0061] More specifically, turn to Figure 5 In the core data assimilation analysis process of the data assimilation module 124, the data assimilation module 124 can receive historical and real-time sensor data from the sensor data storage device 118 of the local data assimilation analysis 104 at 502. At 504, the sensor data can be filtered and include an indication of its uncertainty. The data assimilation module 124 can additionally receive model predictions at 506. The model predictions can be provided by the physical model module 126 and the forcing and boundary condition module 128.

[0062] At 508, the data assimilation module 124 may combine the sensor data and metadata to improve the model results. The data assimilation module 124 may optimize the results by adjusting the data assimilation parameters at 510 and by providing feedback at 512 to adjust the filtering / uncertainty estimation process (eg, provided at the sensor level).

[0063] Figure 6 Another example computing system according to one embodiment is shown, such as can be implemented using a networked environment. As shown, computing environment 600 includes client computer 605, web server 610, server 615, application 616, and application server 620. Client computer 605 can be a physical system (e.g., a desktop computer, a laptop computer, a mobile device, etc.) or a virtual computing instance executed in the cloud. Client computer 605 includes web browser 607. A user can access data services through web browser 607 on network 625 (e.g., the Internet).

[0064] For example, a user may access a web service 612 executing on a web server 610. In one embodiment, the web service 612 provides a web interface for an application server 620 (e.g., executing an application service 622). More specifically, the application service 622 provides a database 624. The database 624 may include data that is presented to the user on the web browser 607.

[0065] Figure 7 Further shown is a server 715 according to one embodiment, such as Figure 6The server 615 of FIG. 706 is a server 615. The server 715 typically includes a processor 704, a network interface device 718, a storage device 708, an input device 721, and an output device 724 connected to the memory 706 via a bus. The server 715 is typically under the control of an operating system. Examples of operating systems include UNIX operating systems, versions of Microsoft Windows operating systems, and releases of Linux operating systems (UNIX is a registered trademark of the Open Group in the United States and other countries, and Microsoft and Windows are trademarks of Microsoft Corporation in the United States, other countries, or both. Linux is a registered trademark of Linux Torvalds in the United States, other countries, or both). More generally, any operating system that supports the functions disclosed herein can be used. The included processor 704 represents a single CPU, multiple CPUs, a single CPU with multiple processing cores, etc. Similarly, the memory 706 can be a random access memory. Although the memory 706 is shown as a single identity, it should be understood that the memory 706 can include multiple modules, and the memory 706 can exist at multiple levels from high-speed registers and caches to lower-speed but larger DRAM chips. The network interface device 718 may be any type of network communication device that allows the navigation server 710 to communicate with other computers via the network 525 .

[0066] Storage device 708 may be a persistent storage device. Although storage device 708 is shown as a single unit, storage device 708 may be a combination of fixed and / or removable storage devices, such as fixed disk drives, solid-state drives, removable memory cards, optical storage, and network storage systems.

[0067] As shown, memory 706 contains application 717 , which may be an application typically executed to take the actions described herein. Storage device 708 contains algorithm 714 , filtered measurements 717 , and uncertainty features 719 .

[0068] Input device 721 may provide a keyboard and / or a mouse, etc. Output device 724 may be any conventional display screen. Although shown separately from input device 721, output device 724 and input device 721 may be combined. For example, a display screen with an integrated touch screen may be used.

[0069] The description of various embodiments of the present invention has been given for the purpose of illustration, but it is not intended to be exhaustive or limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope of the described embodiments. The terms used herein are selected to best explain the principles of the embodiments, practical applications, or technical improvements existing in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

[0070] Below, reference is made to the embodiments presented in the present disclosure. However, the scope of the present disclosure is not limited to the specifically described embodiments. On the contrary, any combination of the following features and elements, whether or not related to different embodiments, is intended to be used to implement and practice the intended embodiments. In addition, although the embodiments disclosed herein can achieve advantages over other possible solutions or prior art, whether a given embodiment achieves a specific advantage does not limit the scope of the present disclosure. Therefore, the following aspects, features, embodiments and advantages are merely illustrative and are not considered to be elements or limitations of the appended claims unless expressly stated in the claims. Similarly, reference to the "present invention" should not be interpreted as a generalization of any inventive subject matter disclosed herein, and should not be considered to be elements or limitations of the appended claims unless expressly stated in the claims.

[0071] Aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, which may be collectively referred to herein as a "circuit," "module," or "system."

[0072] The present invention may be a system, method and / or computer program product. The computer program product may include a computer-readable storage medium (or multiple media) having computer-readable program instructions thereon, the computer-readable program instructions being used to cause a processor to perform various aspects of the present invention.

[0073] A computer readable storage medium may be a tangible device that is capable of retaining and storing instructions for use by an instruction execution device.

[0074] The computer-readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of computer-readable storage media includes the following: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device such as a punch card or a raised structure in a groove with instructions recorded thereon, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium should not be interpreted as a temporary signal itself, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagated through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0075] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to a corresponding computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical transmission fibers, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in a computer-readable storage medium within the corresponding computing / processing device.

[0076] The computer-readable program instructions for performing the operation of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​(e.g., Smalltalk, C++, etc.) and conventional procedural programming languages ​​(e.g., "C" programming languages ​​or similar programming languages). The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the latter case, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider via the Internet). In some embodiments, in order to perform various aspects of the present invention, an electronic circuit including, for example, a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA) may execute computer-readable program instructions to personalize the electronic circuit by utilizing the state information of the computer-readable program instructions.

[0077] Various aspects of the present invention are described herein with reference to the flow charts and / or block diagrams of the methods, devices (systems) and computer program products according to embodiments of the present invention. It will be appreciated that each frame of the flow charts and / or block diagrams and the combination of frames in the flow charts and / or block diagrams can be implemented by computer-readable program instructions.

[0078] These computer-readable program instructions may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions executed by the processor of the computer or other programmable data processing apparatus create a device for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0079] These computer-readable program instructions may also be stored in a computer-readable storage medium, which may direct a computer, a programmable data processing apparatus and / or other device to work in a specific manner, so that the computer-readable storage medium in which the instructions are stored includes an article of manufacture, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0080] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable apparatus, or other device to produce a computer-implemented process, so that the instructions executed on the computer, other programmable apparatus, or other device implement the functions / actions specified in one or more boxes of the flowchart and / or block diagram.

[0081] Flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present invention.In this regard, each frame in flow chart or block diagram can represent the module, segment or part of instruction, and it comprises one or more executable instructions for realizing the logical function of appointment.In some alternative embodiments, the function mentioned in the frame can not occur in the order mentioned in the figure.For example, two frames shown continuously can actually be performed substantially simultaneously, or these frames can sometimes be performed in reverse order, and this depends on the function involved.It can also be noted that the combination of the frame in each frame of block diagram and / or flow chart illustration and block diagram and / or flow chart illustration can be realized by the dedicated hardware-based system of performing specified function or action or performing the combination of special hardware and computer instruction.

[0082] Embodiments of the present invention may be provided to end users via a cloud computing infrastructure. Cloud computing generally refers to the provision of scalable computing resources as a service over a network. More formally, cloud computing may be defined as providing an abstraction of computing power between computing resources and their underlying technology architecture (e.g., servers, storage devices, networks), thereby enabling convenient on-demand network access to a shared pool of configurable computing resources that can be quickly provisioned and released with minimal management effort or service provider interaction. Thus, cloud computing allows users to access virtual computing resources (e.g., storage, data, applications, and even complete virtualized computing systems) in a "cloud" without regard to the underlying physical systems (or the location of those systems) used to provide the computing resources.

[0083] Typically, cloud computing resources are provided to users on a pay-per-use basis, where users are charged only for the computing resources actually used (e.g., the amount of storage space consumed by the user or the number of virtualized systems instantiated by the user). Users can access any resource residing in the cloud at any time and from anywhere on the Internet. In the context of the present invention, users can access applications (e.g., threshold adjustment algorithms) or related data available in the cloud. For example, Figure 1 The module may be executed on a computing system in the cloud. In this case, the threshold adjustment algorithm may adjust the response threshold and store the new value at a storage location in the cloud. Doing so allows a user to access the information from any computing system attached to a network (e.g., the Internet) connected to the cloud.

[0084] Although the foregoing relates to embodiments of the present invention, other and further embodiments of the present invention may be devised without departing from the basic scope of the present invention. Although certain embodiments may be applicable to spoken language systems, the claims are not limited to or even particularly applicable to spoken language interfaces. In one example, embodiments of the method may not involve speech modalities. Therefore, the scope thereof is determined by the appended claims.

Claims

1. A method for modeling a system to assess the state of a physical system, the system having a sensor network component, a core analysis component, and an edge analysis component, the method comprising: The core analysis component uses a calibrated model of the physical system to generate model predictions; determining, at a first sensor of a plurality of sensors connected to a routing node, an uncertainty quantification of the first sensor by estimating uncertainty of data points in a raw data set collected by monitoring the physical system at the first sensor, wherein the uncertainty is estimated during a filtering process at the first sensor to reduce noise in the raw data set, the plurality of sensors and the routing node being members of the sensor network component, wherein the uncertainty quantification is determined in real time using the raw data set and the filtering process; combining, by the core analysis component, the uncertainty quantification with the model prediction to generate a corrected model prediction representing a state of the physical system; adjusting parameters of a raw data assimilation process at the core analysis component based on feedback from the sensor network component; as well as Based on the feedback from the core analysis component, at least one of a type and a parameter of a filtering algorithm of a filtering process at a first sensor of the sensor network component is adjusted by an edge gateway of the edge analysis component.

2. The method according to claim 1, further comprising: The raw data and the uncertainty quantification are reported in real time by the plurality of sensors. The method of claim 1 , wherein the corrected model predictions are output.

4. The method according to claim 3, further comprising: Execution at the first sensor is modified based on the accuracy of the corrected model prediction.

5. The method of claim 3, wherein the parameters of the assimilation process are related to the covariance calculation used to assimilate the original data.

6. The method of claim 1, wherein the physical system comprises a natural force of at least one of: a geographic area, a water system, a gravity system, a thermal system, and a wind system.

7. A system for evaluating a state of a physical system, the system comprising: a sensor network assembly including a routing node and a plurality of sensors connected to the routing node, the plurality of sensors including a first sensor configured to determine an uncertainty quantification of the first sensor by estimating uncertainty of data points in a raw data set collected by monitoring the physical system at the first sensor, wherein the uncertainty is estimated during a filtering process at the first sensor to reduce noise in the raw data set, wherein the uncertainty quantification is determined in real time using the raw data set and the filtering process; A core analysis component comprising a calibrated model of a physical system, wherein the calibrated model can be used to generate model predictions, the core analysis component being configured to: combining the uncertainty quantification with the model prediction to generate a corrected model prediction representing a state of the physical system; and adjusting parameters of the raw data assimilation process based on feedback from the sensor network components; as well as An edge analysis component, including an edge gateway, is configured to adjust at least one of a type and a parameter of a filtering algorithm of a filtering process at a first sensor of the sensor network component based on feedback from the core analysis component.

8. The system of claim 7, wherein the plurality of sensors are configured to report in real time.

9. The system according to claim 7, wherein: The corrected model predictions are output.

10. The system according to claim 9, wherein: Execution at the first sensor is modified based on the accuracy of the corrected model prediction.

11. The system of claim 9, wherein parameters of the assimilation process are modified based on the accuracy of the corrected model predictions, wherein the parameters of the assimilation process are related to covariance calculations used when assimilating the raw data.

12. The system of claim 7, wherein the physical system comprises a natural force of at least one of: a geographic area, a water system, a gravity system, a thermal system, and a wind system.

13. The system of claim 7, wherein the state is output and modified by adjusting parameters of the assimilation process.

14. A computer program product for modeling a system to assess a state of a physical system, the computer program product comprising: A computer readable storage medium readable by a processing circuit and storing instructions for execution by the processing circuit for performing the method according to any one of claims 1 to 6.

15. A computer program product stored on a computer readable medium and loadable into the internal memory of a digital computer, comprising software code portions for executing the method according to any one of claims 1 to 6 when said software code portions are run on a computer.

Images