Patent Issued for Digital platform using cyber-physical twin structures providing an evolving digital representation of a risk-related real world asset for quantifying risk measurements, and method thereof (USPTO 11868684): Swiss Reinsurance Company Ltd.

2024 JAN 25 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- According to news reporting originating from Alexandria, Virginia, by NewsRx journalists, a patent by the inventor Fasano, Pierluigi (Zurich, CH), filed on October 19, 2020, was published online on January 9, 2024.

The assignee for this patent, patent number 11868684, is Swiss Reinsurance Company Ltd. (Zurich, Switzerland).

Reporters obtained the following quote from the background information supplied by the inventors: “In all fields of technology, it is often a requirement to make assessment and/or predictions regarding the evolving operation or status of real world physical systems, assets or living objects, such as electro-mechanical systems, product processing systems, time characteristics and temporal behavior of buildings and constructions, or human beings or animals based on measured parameters and sensory data, for example for cyber-physical manufacturing, precise personalized and predictive medicine (e.g. telematics based), floating short or long scale risk assessment and measurements of physical real-world assets, or augmented or mixed reality technologies. For example, it may be desirable to automatically predict a remaining useful life of a technical system operatable within an acceptable failure risk, such as an aircraft engine, to help plan when the system should be replaced. Further, an operator of a system or physical asset may want to monitor a condition or a portion of the system or physical asset, to allow for conducting proper technical maintenance, etc. However, despite the improvements in sensor and computer technologies, accurately making such risk assessments and/or predictions is still a difficult technical task. For example, an event that occurs while a system or physical asset is not operating may also impact the remaining useful life and/or condition of the system or asset but are not taken into account by typical approaches in the prior art.

“A real world physical system can be associated with asset’s or system’s components, such as sensors and actuators. Example of these are smart homes or Advance Driver Assistance Systems (ADAS) of cars. The monitored systems and assets can be spatially distributed and, thus, these systems and assets include components and subsystems that are also spatially distributed. As a consequence, there may be a need to provide an appropriate information transportation and distribution that serves to sense and transmit measuring parameter values and data, and control the spatially distributed components and subsystems in order for the system or asset to function efficiently and safely. In the state of the art, despite the fact that IoT provides a new dimension of connectivity, there is still a great need for systems and technologies that provides connectivity and computational intelligence for the system’s components that are connected to the IoT. It is therefore a demand to provide technical systems and methods to allow technical assessments and/or automated predictions and forecasts for physical systems e.g. associated with the IoT in an automatic and technically precise manner relying on measured physical parameters.

“Another technical problem to provide such systems is, that the number of factors and parameters to monitor, assess and/or monitor e.g. for securing maintenance and/or to operate real world physical or intangible assets or objects as e.g. large, complex industrial systems and their associated apparatuses such as engines or product processing devices etc., or to continuously monitor physical medical condition parameters of living objects such as human beings or animals, in particular for interventions and optimization based on such factors (for example for asset utilization, consumption reduction, preventive measures, physical inspections, physical damage state assessment work-scope, and operation capacity etc.) is often that large that it has to be performed in nature and in loco and is time-consuming and technically complex. Thus, it is another requirement to provide technical systems and methods to allow technical assessments and/or automated predictions and forecasts for the evolution of physical systems.

“Finally, the machine-based prediction or forecast of occurrence probabilities for events causing impacts, i.e. occurring risks, is technically difficult to be realized because of their long-tail nature and their susceptibility to measuring and parametrizing quantitative impact factors and to capturing temporal time developments and parameter fluctuations. Automation of prediction and modeling of catastrophes and risk accumulation is especially challenging as there is limited historic loss data available, and new risk events with new characteristics keep emerging. In addition to finding, triggering and/or mitigating valuable loss and exposure data where existing, it is therefore important to reduce the reliance on historic data by using novel modelling techniques going beyond traditional data analysis and predictive modeling approaches and techniques by monitoring a controllable cause-effect chain. Risk driven systems have been developed and used triggered and signaled by automated forecast systems. Such systems are able to predictively and quantitatively generate expected occurrence probability of physical events and their impact such as losses to physical assets and objects typically starting from a set of modelling scenarios, which heavily depend in their timely development on the modelling technique. So there is a further requirement, to provide a new technical system to overcome these problems.

“Digital representations (avatars) of twinned physical real-world assets and objects are herein referred as digital twins, i.e. an evolving digital data representation of a historical and current behavior of the twinned physical real-world asset and object or process. Thus, a digital representation of twinned physical real-world asset and object is the exact digital replica of the twinned physical real-world asset and object. The resulting digital avatar allows directly linking modelling structures and simulation techniques with sensors and big data. For example, the digital twin of an automobile is a digital, 3D representation of every part of the vehicle, technically replicating the physical world so accurately that a human could virtually operate the vehicle exactly as she/he would in the physical world and get the same responses, digitally simulated. It is to be noted, that in this applications, physical assets may also refer to physical processes, which are digitally twinned. Further, in this application, the sophisticate digital twins may continuously pull real-time sensor and systems data to provide precise snapshots of the physical twin’s current state. These data can then be integrated with historical data and predictive technologies allowing to provide signals related to potential issues and/or trigger the indication of solutions. The inventive solution of this application based on the provided digital risk twin technology can profoundly enhance the ability to make or trigger proactive, measuring data-driven decisions, increasing efficiency and avoiding potential issues by reducing the risk measure provided by the inventive system. In fact, the invention enables to explore possible futures by exploring what-if scenarios based on the current measuring state of the asset of object and the evolving state of the digital avatar representation.”

In addition to obtaining background information on this patent, NewsRx editors also obtained the inventor’s summary information for this patent: “It is an object of the invention to allow for systematic capturing, measuring, quantifying, and forward-looking generating of appropriate risk and risk accumulation measures of physical real-world assets and objects based on physical measuring parameter values and data. Further, the system should be able to connect directly to the core flow of data of the present digital society e.g. using wearables, quantified-self, Internet of Things, smart cities, and industry 4.0 technologies, etc.) by providing a new technology for automated digital risk assessment and forecasting platforms. It is a further object of the invention to allow ensuring the accumulation of quality data which is critical for understanding, identifying, and developing more precise technical instruments and systems to monitor and assess occurrence probabilities and events risks in the age of big data, industry 4.0 and broad mobile internet connectivity e.g. 5G data networks, where the increased bandwidth enables machines, robots and other assets or objects with a high sensory environment, as smart homes and smart cities to collect and transfer more data than ever. The invention should thus be scalable, and the used simulation technics should be easily accessible to the physical assets’ analytics. The invention should in particular allow for a normalization of the used risk factors and measuring values. Further, the invention should be easily integratable in other processes, productions chains or risk assessment and measuring systems. Finally, the invention should be enabled to use data and measuring parameter values from multiple heterogeneous data sources, inter alia from IoT sensory. The probability measures and risk forecasts should allow to capture various device and environmental structures, providing a precise and reproducible measuring of risk factors, and allowing to optimize associated event occurrence impacts of the captured risk events.

“According to the present invention, these objects are achieved particularly through the features of the independent claims. In addition, further advantageous embodiments follow from the dependent claims and the description.

“According to the present invention, the abovementioned objects are particularly achieved by the digital platform for avatar measurements of evolving risk-based real-world measuring parameters, the digital platform comprising at least one input device or measuring sensor associated with a specific physical or intangible real-world asset or living object to be monitored, in that the digital platform comprises a data store storing modular digital assets/objects elements each representing a plurality of subsystems of the real-world asset or object for the assembly of a digital twin representation of the physical or intangible real-world assets or living objects, wherein the modular digital assets or objects elements are selectable to be assembled to said digital twin representation from the data store based on captured structural, operational and/or environmental parameters by means of the digital platform, in that by means of the at least one input device or sensor associated with the twinned physical asset or object, structural, operational and/or environmental status parameters of the real-world asset or object are measurable, and transmittable to the digital platform, to be associated to the digital twin representation, wherein the values of the status parameters associated with the digital twin representation are dynamically monitored and adapted based on the transmitted parameters, and wherein the digital twin representation comprises data structures representing states of each of the plurality of subsystems of the real-world asset or object holding the parameter values as a time series of a time period, in that, by means of the digital platform, data structures representing future states of each of the plurality of subsystems of the real-world asset or object are generatable as value time series over a future time period based on an application of simulations using cumulative damage models, the cumulative damage models generating the effect of the operational and/or environmental asset or object parameters on the twinned real-world asset or object of the future time period, and in that, by means of the digital platform, the digital twin representation is analyzable providing a measure for a future state or operation of the twinned real-world asset or object based on the generated value time series of values over said future time period, the measure being related to the probability of the occurrence of a predefined event to the real-world asset or object.

“In an embodiment variant, the control of an operation or status of the real world asset or object is optimized or adjusted to predefined operational and/or status asset or object parameters of the specific real-world asset or object based on the provided measure for a future state or operation of the twinned real-world asset or object and/or based on the generated value time series of values over said future time period, wherein in case of an optimized control of operation, the optimized control of operation is generated to jointly and severally increase the specific operating performance criteria in time and future of the real-world asset or object or decrease a measure for an occurrence probability associated with the operation or status of the real-world asset or object within a specified probability range.

“Further, the decrease of the measure for an occurrence probability associated with the operation or status of the real-world asset or object can be based on a transfer of risk to an automated risk-transfer system controlled by the digital platform, wherein values of parameters characterizing the transfer of risk are optimized based on said measure for a future state or operation of the twinned real-world asset or object and/or based on the generated value time series of values over said future time period. In order to optimize the status of the real-world asset or object or the probability of an occurrence of a predefined risk event, an optimizing adjustment of at least a subsystem of the real-world asset of object can be triggered by means of the digital platform. The triggering by means of the digital platform can e.g. be performed by electronic signal transfer. Based on the measure for a future state or operation of the twinned real-world asset or object, a forecasted measure of an occurrence probability of one or more predefined risk events impacting the real-world asset or object can be generated by propagating the parameters of the digital twin representation in controlled time series.”

The claims supplied by the inventors are:

“1. A method for a digital device to measure temporally evolving parameters, the method comprising: selecting, by circuitry of the digital device, object elements stored in a storage of the digital device, and assembling the selected object elements; measuring, by a plurality of sensors of the digital device, at least one parameter of structural parameter, operational parameter, and environmental status parameter, the at least one parameter being associated with a physical object represented by the assembled object elements, wherein the assembled object elements include data structure representing states of subsystems of the physical object, and the data structure holds a value of the at least one parameter; generating the data structure based on simulated effects of the at least one parameter on the physical object; analyzing the physical object based on the generated data structure for a future time period; predicting, based on analysis, an estimated probability of an occurrence of a predefined physical event with a certain strength or physical characteristic physically impacting the physical object by associated losses or predicting, based on the analysis, the probability of the occurrence of a predefined state to the physical object in the future time period, wherein a physically measurable probability for the occurrence of the predefined physical event is established based on the measured at least one parameter and based on frequency and severity of historical measuring data of the predefined physical event by a predicting machine learning module using measured historical timeseries data; and triggering an adjustment of a subsystem of the physical object via an electronic signal transfer to optimize a status of the physical object based on the estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object and the physically measurable probability.

“2. The method according to claim 1, further comprising: adjusting an operation of the physical object based on the predicted estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period, wherein the operation is adjusted to jointly and severally increase operation performance criteria or decrease the estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period.

“3. The method according to claim 2, wherein the decrease of the estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period is based on a transfer of risk to an automated risk-transfer system controlled by the digital device, further comprising: optimizing values of parameters characterizing the transfer of risk based on the generated data structure.

“4. The method according to claim 1, further comprising: propagating parameters associated with the physical object for predicting the estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period.

“5. The method according to claim 1, wherein the operational parameter and environmental status parameter comprise endogen parameters, whose values are determined by the physical object or exogen parameters, whose values origin from and are determined outside the physical object and are imposed on the physical object.

“6. The method according to claim 5, wherein the digital device comprises exteroceptive sensors for sensing exogen environmental parameters physically impacting the physical object and proprioceptive sensors sensing endogen operating or status parameters of the physical object.

“7. The method according to claim 5, wherein the plurality of sensors comprise interfaces for setting one or more wireless or wired connections between the digital device and the sensors, and data links are set by the wireless or wired connections between the digital device and the sensors associated with the physical object transmitting the exogen and endogen parameters measured or captured by the sensors to the digital device.

“8. The method according to claim 1, wherein the digital device triggers an automated expert system of the digital device with an electronic signal transfer, and the digital device triggers transmitting a digital recommendation to a user interface generated by the expert system of the digital device based on the predicted estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period and the digital recommendation comprises indications for an optimization of the physical object or adaption of the at least one of the structural parameter, operational parameter, and environmental status parameter.

“9. A digital device comprising: circuitry configured to select object elements stored in a storage of the digital device, and assemble the selected object elements; a plurality of sensors configured to measure at least one parameter of structural parameter, operational parameter, and environmental status parameter, the at least one parameter being associated with a physical object represented by the assembled object elements, wherein the assembled object elements include data structure representing states of subsystems of the physical object, and the data structure holds a value of the at least one parameter; and the circuitry further configured to: generate the data structure based on simulated effects of the at least one parameter on the physical object, analyze the physical object based on the generated data structure for a future time period, predict, based on analysis, an estimated probability of an occurrence of a predefined physical event with a certain strength or physical characteristic physically impacting the physical object by associated losses or predicting, based on the analysis, the probability of the occurrence of a predefined state to the physical object in the future time period, wherein a physically measurable probability for the occurrence of the predefined physical event is established based on the measured at least one parameter and based on frequency and severity of historical measuring data of the predefined physical event by a predicting machine learning module using measured historical timeseries data, and trigger an adjustment of a subsystem of the physical object via an electronic signal transfer to optimize a status of the physical object based on the estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object and the physically measurable probability.

“10. The digital device according to claim 9, wherein the circuitry is further configured to adjust an operation of the physical object based on the predicted estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period, and the operation is adjusted to jointly and severally increase operation performance criteria or decrease the estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period.

“11. The digital device according to claim 10, wherein the decrease of the estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period is based on a transfer of risk to an automated risk-transfer system controlled by the digital device, and the circuitry is further configured to optimizing values of parameters characterizing the transfer of risk based on the generated data structure.

“12. The digital device according to claim 9, wherein the circuitry is further configured to propagate parameters associated with the physical object for predicting the estimated probability of the occurrence of the predefined physical event or the probability of the occurrence of the predefined state to the physical object in the future time period.

“13. The digital device according to claim 9, wherein the operational parameter and environmental status parameter comprise endogen parameters, whose values are determined by the physical object or exogen parameters, whose values origin from and are determined outside the physical object and are imposed on the physical object.

“14. The digital device according to claim 13, wherein the plurality of sensors include at least exteroceptive sensors for sensing exogen environmental parameters physically impacting the physical object and proprioceptive sensors sensing endogen operating or status parameters of the physical object.

“15. The digital device according to claim 13, wherein the plurality of sensors comprise interfaces for setting one or more wireless or wired connections between the digital device and the sensors, and data links are set by the wireless or wired connections between the digital device and the sensors associated with the physical object transmitting the exogen and endogen parameters measured or captured by the sensors to the digital device.”

There are additional claims. Please visit full patent to read further.

For more information, see this patent: Fasano, Pierluigi. Digital platform using cyber-physical twin structures providing an evolving digital representation of a risk-related real world asset for quantifying risk measurements, and method thereof. U.S. Patent Number 11868684, filed October 19, 2020, and published online on January 9, 2024. Patent URL (for desktop use only): https://ppubs.uspto.gov/pubwebapp/external.html?q=(11868684)&db=USPAT&type=ids

(Our reports deliver fact-based news of research and discoveries from around the world.)