Data efficient tool for predicting failures under dynamic operating conditions

Abstract

Lack of data, among other technical issues, can make it difficult or impossible to properly predict the degradation over time of various physical components or equipment. A failure prognostics system includes a degradation evolution model and a parametric model. The system can obtain the one or more physical quantities of a physical system, and train the parametric model with the one or more physical quantities of the physical system. The system can calibrate the degradation evolution model with one or more calibration parameters that are output from the parametric model. Furthermore, the system can generate a degradation output from the degradation evolution model that predicts a degradation of the physical system over time. In some cases, based on the degradation output, the system triggers an action to replace or repair a portion of the physical system.

Description

Docket No. 202410333DATA EFFICIENT TOOL FOR PREDICTING FAILURESUNDER DYNAMIC OPERATING CONDITIONSBACKGROUND

[0001] Various technical problems need to be addressed to accurately predict the degradation of various physical components (e.g., electronic components) under time-varying loads (e.g., thermal loads). Accurate predictions can result in increased efficiency of predictive maintenance practices in various industries. Such predictions are particularly valuable when faults can be detected ahead of time based on a time-varying analysis of degradation. Predicting anomaly or faulty behavior can generally be defined as an event or occurrence that does not follow expected or normal behavior. In the context of neural networks or machine learning, an anomaly can be difficult to define, but the definition can be critical to the success and effectiveness of a given fault predictor. An efficient fault predictor should be capable of differentiating between faulty and normal instances with high precision and accuracy, so as to detect as many as possible of the fault instances while avoiding false alarms. Supervised learning models, for instance models for fault prediction, typically require large amounts of data to be trained. It is recognized herein, however, that acquiring and storing sensor data is often expensive or cost-prohibitive. Furthermore, instances of time series data in the field corresponding to faulty behaviors or degradation tend to be scarce. For example, various machines and systems are typically expected to operate in the field normally the vast majority of the time, such that faults and degradation are an exception in healthy environments. This lack of data problem, among other technical issues, can make it difficult or impossible to properly characterize or model degradation of various physical components under time-varying loads.BRIEF SUMMARY

[0002] Embodiments of the invention address and overcome one or more of the described- herein shortcomings by providing methods, systems, and apparatuses that improve fault or degradation prediction.

[0003] In an example aspect, a failure prognostics system includes a degradation evolution model and a parametric model. The system can further include a sensor configured to capture real samples of data from a physical system. The real samples of data are representative ofDocket No. 202410333 one or more physical quantities of the physical system. The system can further include a memory storing instructions that, when executed by the processor, cause the processor to perform various operations. The operations can include obtaining the one or more physical quantities of the physical system, and training the parametric model with the one or more physical quantities of the physical system. The system can calibrate the degradation evolution model with one or more calibration parameters that are output from the parametric model. Furthermore, the system can generate a degradation output from the degradation evolution model that predicts a degradation of the physical system over time. In some cases, based on the degradation output, the system triggers an action to replace or repair a portion of the physical system.

[0004] In another example aspect, the parametric model defines a first artificial neural network (ANN) configured to generate a latent space representation based on the one or more physical quantities of the physical system. The parametric model can further define a second ANN coupled to the first ANN. The second ANN can be configured to generate the one or more calibration parameters based on the latent space representation. The operations further include obtaining operation condition data representative of one or more operating conditions within the physical system. Data representative of operating conditions can come from sensors (e.g., load or temperature sensors), industrial processes (e.g., digital information), or manual input (e.g., a load setting for a given process). The operating condition data and the latent space representation can be into the second ANN, such that the calibration parameters are based on the operating condition data and latent space representation. By way of example, the physical system can include a bearing component, and the degradation output can predict the degradation of the bearing component due to thermal stress fatigue.BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

[0005] The foregoing and other aspects of the present invention are best understood from the following detailed description when read in connection with the accompanying drawings. For the purpose of illustrating the invention, there is shown in the drawings embodiments that are presently preferred, it being understood, however, that the invention is not limited to the specific instrumentalities disclosed. Included in the drawings are the following Figures:

[0006] FIG. 1 is a block diagram of an example system that includes a failure diagnostics or prognostics computer system configured to predict degradation of physical components over time, in accordance with an example embodiment.Docket No. 202410333

[0007] FIG. 2 is a block diagram that shows an example pipeline for training and operating the degradation model, in accordance with an example embodiment.

[0008] FIG. 3 is a block diagram that shows example training and inference inputs and outputs of the Al model and the degradation model, in accordance with an example embodiment.

[0009] FIG. 4 illustrates a computing environment within which embodiments of the disclosure may be implemented.DETAILED DESCRIPTION

[0010] As an initial matter, variations of anomaly, fault, failure, and degradation can be used interchangeably herein without limitation, unless otherwise specified. Fault diagnostics and failure prognostics of equipment and systems (predictive maintenance, prognostics and health management (PHM), etc.) have been the subject of active investigation and intense real world solution development during the recent decades. It is recognized herein that failure estimation of physical components often relies on limited measurements from physical sensors, or computationally expensive simulations that require expertise and labor to setup and run. It is further recognized herein that artificial intelligence (Al) tools using data only processes are typically difficult to train and validate, due to the lack of relevant data. Further still, it is recognized herein that the accuracy of available physics-based models for degradation can be limited, such that current approaches lack quality models for predicting failures in specific real- world applications.

[0011] In accordance with various embodiments, a physics informed Al tool can be trained on physical laws and calibrated on limited experimental data. The tool can effectively predict degradations or faults in physical components in various scenarios, for instance when the physics-based information concerning the given degradation is inaccurate or when the related experimental data is limited.

[0012] Referring initially to FIG. 1 , an example automation or industrial network or physical system 100 can include one or more plants or production networks 104 that contain control logic, host web servers, and the like. For example, the physical system 100 can include an enterprise or IT network 102 and multiple operational plant or production networks 104 communicatively coupled to the IT network 102. The production network 104 or enterprise network 102 can include one or more failure diagnostics or prognostics computer systems or modules 106 connected within the production network 104. The computer system 106 can define a degradation model or tool 107, as further described herein. An example computerDocket No. 202410333 system 106 is connected to the IT network 102. The arrangement of the computer system 106 can vary as desired, and all such arrangements are contemplated as being within the scope of this disclosure. For example, in some cases, data augmentation and model training described herein can be performed on a different system than the system that monitors a physical system and collects the data from the physical system. In other cases, the system that collects the data can also augment the data and train the models.

[0013] Still referring to FIG. 1 , the production network 104 can include various production machines configured to work together to perform one or more manufacturing operations. Example production machines of the production network 104 can include, without limitation, robots 108 and other field devices that can be controlled by a respective PLC 114, such as sensors 110, actuators 112, or other machines, such as automatic guided vehicles (AGVs) 108. The PLC 1 14 can send instructions to respective field devices. In some cases, a given PLC 114 can be coupled to a human machine interfaces (HMIs) 116. It will be understood that the physical system 100 is simplified for purposes of example. That is, the physical system 100 may include additional or alternative nodes or systems, for instance other network devices, that define alternative configurations, and all such configurations are contemplated as being within the scope of this disclosure.

[0014] The network or system 100, in particular each production network 104, can define a field portion or level 1 18 and plant level or portion 120. For example, and without limitation, the plant level 120 can define one or more industrial plants or systems that can be geographically and functionally separate from or independent of each other. For example, the plant level 120 can include Brownfield plants and Greenfield plants that are each connected to respective field devices within the field level 118. The field level 118 can include various field devices such as the robots 108, PLC 114, sensors 110, actuators 112, HMIs 116, and AGVs. The sensors 110 can be configured to capture real samples of time series data from the physical system 100. The field portion 1 18 can define one or more production lines or control zones associated with a given plant in the plant level 120. The PLC 1 14, sensors 110, actuators 112, and HMI 1 16 within a given production line can communicate with each other via a respective field bus 122. Each control zone can be defined by a respective PLC 114, such that the PLC 1 14, and thus the corresponding control zone, can connect to the respective plant portion 120 via an Ethernet connection 124. In some cases, the robots 108 and AGVs can be configured to communicate with other devices within the fieldbus portion 118 via a WiFi connection 126. Similarly, the robots 108 and AGVs can communicate with the Ethernet portion 120, in particular a Supervisory Control and Data Acquisition (SCADA) server 128, via the Wi-Fi connection 126. In various examples, a respective computer system 106 isDocket No. 202410333 communicatively coupled between the PLC 114 and the respective plant in the plant level 120, for instance via the Ethernet connection 124 or the Wi-Fi connection 126. In some examples, the computer system 106 is defined by the PLC 114.

[0015] The plant level 120 of a given production network 104 can include various computing devices or subsystems communicatively coupled together via the Ethernet connection 124. Example computing devices or subsystems in the plant portion 120 include, without limitation, a mobile data collector 130, HMIs 132, the SCADA server 128, the computing system 106, a wireless router 134, a manufacturing execution system (MES) 136, an engineering system (ES) 138, and a log server 140. The ES 138 can include one or more engineering works stations. In an example, the MES 136, HMIs 132, ES 138, and log server 140 are connected to the production network 104 directly. The wireless router 134 can also connect to the production network 104 directly. Thus, in some cases, mobile users, for instance the mobile data collector 130 and robots 108 (e.g., AGVs), can connect to the production network 104 via the wireless router 134.

[0016] It will be appreciated that the program modules, applications, computer-executable instructions, code, or the like depicted herein are merely illustrative and not exhaustive, and that processing described as being supported by any particular module may alternatively be distributed across multiple modules or performed by a different module. In addition, various program module(s), script(s), plug-in(s), Application Programming Interface(s) (API(s)), or any other suitable computer-executable code may be provided to support functionality provided by the program modules, applications, or computer-executable code depicted herein and / or additional or alternate functionality. Further, functionality may be modularized differently such that processing described as being supported collectively by the collection of program modules depicted herein may be performed by a fewer or greater number of modules, or functionality described as being supported by any particular module may be supported, at least in part, by another module. In addition, program modules that support the functionality described herein may form part of one or more applications executable across any number of systems or devices in accordance with any suitable computing model such as, for example, a client-server model, a peer-to-peer model, and so forth. In addition, any of the functionality described as being supported by any of the program modules depicted herein may be implemented, at least partially, in hardware and / or firmware across any number of devices, for instance computer system 106.

[0017] Referring also to FIGs. 2 and 3, the diagnostic or prognostics computing system 100 can include various Al models, for instance a trained Al model 202 and the degradation model or tool 107, configured to predict faults or failures. By way of example, the degradation modelDocket No. 202410333107 can predict failures related to semiconductor circuits, among other physical components from other technologies. Electronic circuits are the backbone of most industrial devices and personal gadgets. Thermal energy dissipated from current flow in these devices results in temperature rise, which in turn can lead to mechanical failure from thermal stresses in these cases. Variable loading conditions can lead to unknown temperature distributions, which in turn can cause hot spots that lead to local failure. For example, solders that are used to attach circuits to heat sinks are known to fail often. It is recognized herein that physics informed reconstruction of these temperature distributions ahead of time can help in predicting failure from thermal distributions, if a degradation over time relationship can be established. Additionally, for instance in the absence of sensor readings, training data can be used from simulation models.

[0018] Referring again to FIGs. 2 and 3, the degradation model 107 can be configured to predict degradation as a function of time (e.g., degradation estimates 204). For example, the model 107 can be based on empirical approximations, such as rainflow-counting and Lundberg & Palmgren theory, for calculation of a mechanical bearing fatigue life. Additionally, or alternatively, the model 107 can be based on a physics-of-failure simulations, such as finite element model simulations that enable the identification of mechanical stresses at one or more specific locations. The information used as inputs to the model 107 can depend on operating conditions (e.g., mechanical or electrical load, ambient temperature, etc.) and specific characteristics of the equipment being monitored. The specific characteristics can include various parameters (e.g., the load rating of a bearing), information employed to create a simulation model (e.g., geometry of the parts), or the like. In some cases, experimental data related to the specific equipment type is used to properly calibrate the parameters of the degradation model 107, so the model 107 can provide reliable estimates. Fixed calibration for such models can be defined, but it is recognized herein that fixed calibration might not account for different or varying operating conditions or equipment characteristics.

[0019] Therefore, in accordance with various embodiments, a second model (e.g., Al model 202) can be employed to adapt the degradation model 107 calibration to those varying characteristics, so that the degradation estimates 204 are reliable even when those variations occur. In some examples, for instance for new equipment types, historical operation data is not available for such calibration. It is recognized herein, however, in many industrial domains, experiments are performed to support processes such as design, qualification, and certification. Data from those tests, for instance experimental data 206, can be employed for the calibration of the degradation model 107, including the training of the Al model 202. It is further recognized herein, however, that the actual operating conditions of the equipment are,Docket No. 202410333 in some cases, different from those employed during the related experiments. Therefore, the degradation model 107 and the Al model 202 that are calibrated using the data 206 from such experiments might not perform well if employed during operation. In accordance with various embodiments, the data 206 obtained during those experiments can be used to achieve model calibrations that can result in improved performance in estimating degradation during operation, such that corresponding equipment can be monitored and maintained accurately and efficiently.

[0020] It is recognized herein that previous approaches (e.g., fixed calibration of empirical or analytical curves and equations or physics-of-failure simulations) to determining a relationship between time and evolving degradation are dependent on specific operating conditions, and are often approximations. The Al model 202 can improve various approximate curves by using training from existing experimental data 206 such as, for example, data from endurance testing. Those experiments can produce experimental data 206 associated with run-to-failure conditions, representing the evolution of degradation of relevant failure modes from normal condition to failure. Thus, this data can inform the model 202 about the evolution of such degradation, with the limitations that the operating conditions used for the experiments might not correspond in general to the actual operating conditions existing in the field.

[0021] Referring in particular to FIG. 2, in some examples, the Al model 202 defines a parametric model or artificial neural networks (ANNs) that include a plurality of layers, for instance a first set of ANN layers or first ANN model 208 and a second set of ANN layers or second ANN model 210. The Al model 202 can be trained to produce calibration parameters 212 of the degradation model 107, such that that the degradation model 107 generates reliable degradation estimates 204 under varying operating conditions. Data representative of operating conditions can come from sensors (e.g., load or temperature sensors), industrial processes (e.g., digital information), or manual input (e.g., a load setting for a given process). By way of an example involving a bearing, the degradation estimates 204 might define a current and / or future degree of spalling or corrosion in a race. More generally, the degradation estimates 204 can include any metric that indicates the evolution of a failure mode that at some point in time may lead to failure of the equipment. Current / future degradation information (e.g., degradation estimates 204) can trigger operation or maintenance actions. Example maintenance actions can include performing predictive maintenance and scheduling maintenance at the best opportunity, so as to balance low impact to operation and low risk of failure, which, some cases, can only be achieved with reliable estimates 204 of how the degradation will evolve. Operation-related actions triggered by the degradation estimates 204Docket No. 202410333 can include, for example, switching to an alternative operating mode to delay degradation or to avoid risk of failures while maintenance is not performed.

[0022] With continuing reference to FIG. 2, an example end-to-end pipeline 200 for timeevolution degradation is illustrated that includes a training phase or training operations 201 of ANNs and an interference phase or inference operations 203 of the ANNs. The first set of ANN layers or first ANN model 208 can generate or output a latent space representation 214 from measured physical quantities 216. The measured physical quantities 216 can include temperature readings or a measure of load on a component. By way of example, suppose that the equipment of interest is a bearing, then mechanical loads and ambient temperature might correspond to measurements of operating conditions, and measurements of bearing temperatures and vibration can be indicators of its degradation. The latent space representation 214 generated by the first set of ANN layers 208 can split information into operating condition dependent and other non-dependent variables. For example, the ANNs can be trained based on a loss function that defines what is the goal to achieve in training. By identifying measurable operating conditions that can vary from experiments to operation, and including those as part of the loss function, the latent variables can be split between operating conditions and non-operating conditions. Thus, the loss function in this case can include a term associated with the difference between the operating condition measurements and the corresponding latent variables. This provides means for obtaining latent variables (referred to as other latent variables) that are free of the influence of operating conditions, being a function only of the health state of the equipment. Thus, the split of latent variables enforces that the so called “other latent variables” are not affected by the operating conditions, therefore the solution can be applied independently of the operating conditions that can be plugged in externally.

[0023] Still referring to FIG. 2, the second set of ANN layers 210 can be used to generate or output parameters 212 for the time dependent degradation evolution model 107, from the latent space representations 214 that are input into the second set of ANN layers 210. The training phase 201 of the ANN layers 208 and 210 can be performed end-to-end so that the degradation evolution model 107 is trained by the first and second set of ANN layers 208 and 210, respectively. Once the first and second set of ANNs 208 and 210 are trained during the training 201 , for instance based on known accelerated life test data or simulation data, the models 202 (and thus the models 208 and 210) and 107, can be deployed for the inference operations 203. During inference 203, available measurements or estimations (data) 216 representative of operating conditions are also used to create the relevant value of parameters 212 needed to feed into the degradation evolution model 107. The data 216 associated withDocket No. 202410333 the operating conditions are provided directly as inputs to the model 210, enabling its utilization in conditions that are different from those which are present during the training 201 (e.g., operating conditions vs accelerated life test conditions). During operations 203, the actual operating conditions (e.g., mechanical load or ambient temperature) can be employed instead of the latent variables resulting from the first set of ANN layers 208. The remaining latent variables are thus free of the influence from operating conditions, such that the second set of ANN layers 210 can generate calibration parameters 212 that consider the health state of the equipment, even if operating conditions are different from those used during training 201. Referring again to the bearing example, the degradation estimates can represent estimates of current fatigue and how it is expected to evolve in the future. It will be understood that a bearing is presented by way of example, and that the degradation model 107 can predict degradation of alternative parts or equipment, for instance failures caused by thermal stress in circuit boards or electric equipment, failures of electrical cables or transformers, mechanical failures in gears or the like (e.g., wind turbines), failures in rolling stock for trains, or failures in mechanical (e.g., electro or hydro-mechanical) pneumatic actuators or valves, and all such parts or equipment are contemplated as being within the scope of this disclosure.

[0024] In various examples, physics informed Al can provide data efficiency aspects for creating training data, using governing laws / domain expertise to add additional constraints. Referring again to an example bearing failure, the miner’s rule, or any other failure prediction approximation such as coffin-mansion law, can provide a rough idea of cycles to failure degradation evolution for the component due to thermal stresses. Based on a combination of sensor data and simulation results, the accurate curve for the failure evolution can be learned. Additional physics domain knowledge, such as sampling around areas of higher stress concentrations (e.g., mounting holes) can also augment the process of model training. Embodiments described herein can predict degradation of various physical components exposed to thermal stress related fatigue, such as braking pads in vehicles, bearing failures, etc.

[0025] Thus, the computing system described herein can use a combination of limited data from tests, simulation data, and physics models to generate health monitoring models (e.g., degradation model 107) configured to predict or estimate failure of physical components during load varying operations. Data can be input that is obtained from accelerated tests that are performed during design, qualification / certification, or production. Therefore, run-to-failure data can be made available in a short period of time, so embodiments can enable the development of accurate failure mechanism models, based on time-evolution of degradation, before any equipment fails in the field. In contrast, existing solutions typically rely on first principlesDocket No. 202410333 models or run-to-failure data during normal operation, and both options present serious limitations for creation of accurate models for practical applications as explained herein.

[0026] Thus, as described herein, a failure prognostics system can include a degradation evolution model and a parametric model. The system can further include a sensor configured to capture real samples of data from a physical system. The real samples of data are representative of one or more physical quantities of the physical system. The system can further include a memory storing instructions that, when executed by the processor, cause the processor to perform various operations. The operations can include obtaining the one or more physical quantities of the physical system, and training the parametric model with the one or more physical quantities of the physical system. The system can calibrate the degradation evolution model with one or more calibration parameters that are output from the parametric model. Furthermore, the system can generate a degradation output from the degradation evolution model that predicts a degradation of the physical system over time. In some cases, based on the degradation output, the system triggers an action to replace or repair a portion of the physical system.

[0027] In another example aspect, the parametric model defines a first artificial neural network (ANN) configured to generate a latent space representation based on the one or more physical quantities of the physical system. The parametric model can further define a second ANN coupled to the first ANN. The second ANN can be configured to generate the one or more calibration parameters based on the latent space representation. The operations further include obtaining operation condition data representative of one or more operating conditions within the physical system. Data representative of operating conditions can come from sensors (e.g., load or temperature sensors), industrial processes (e.g., digital information), or manual input (e.g., a load setting for a given process). The operating condition data and the latent space representation can be into the second ANN, such that the calibration parameters are based on the operating condition data and latent space representation. By way of example, the physical system can include a bearing component, and the degradation output can predict the degradation of the bearing component due to thermal stress fatigue.

[0028] FIG. 4 illustrates an example of a computing environment within which embodiments of the present disclosure may be implemented. A computing environment 500 includes a computer system 510 that may include a communication mechanism such as a system bus 521 or other communication mechanism for communicating information within the computer system 510. The computer system 510 further includes one or more processors 520 coupled with the system bus 521 for processing the information. The computer system 106 may include, or be coupled to, the one or more processors 520.Docket No. 202410333

[0029] The processors 520 may include one or more central processing units (CPUs), graphical processing units (GPUs), or any other processor known in the art. More generally, a processor as described herein is a device for executing machine-readable instructions stored on a computer readable medium, for performing tasks and may comprise any one or combination of, hardware and firmware. A processor may also comprise memory storing machine-readable instructions executable for performing tasks. A processor acts upon information by manipulating, analyzing, modifying, converting or transmitting information for use by an executable procedure or an information device, and / or by routing the information to an output device. A processor may use or comprise the capabilities of a computer, controller or microprocessor, for example, and be conditioned using executable instructions to perform special purpose functions not performed by a general purpose computer. A processor may include any type of suitable processing unit including, but not limited to, a central processing unit, a microprocessor, a Reduced Instruction Set Computer (RISC) microprocessor, a Complex Instruction Set Computer (CISC) microprocessor, a microcontroller, an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), a System-on-a- Chip (SoC), a digital signal processor (DSP), and so forth. Further, the processor(s) 520 may have any suitable microarchitecture design that includes any number of constituent components such as, for example, registers, multiplexers, arithmetic logic units, cache controllers for controlling read / write operations to cache memory, branch predictors, or the like. The microarchitecture design of the processor may be capable of supporting any of a variety of instruction sets. A processor may be coupled (electrically and / or as comprising executable components) with any other processor enabling interaction and / or communication therebetween. A user interface processor or generator is a known element comprising electronic circuitry or software or a combination of both for generating display images or portions thereof. A user interface comprises one or more display images enabling user interaction with a processor or other device.

[0030] The system bus 521 may include at least one of a system bus, a memory bus, an address bus, or a message bus, and may permit exchange of information (e.g., data (including computer-executable code), signaling, etc.) between various components of the computer system 510. The system bus 521 may include, without limitation, a memory bus or a memory controller, a peripheral bus, an accelerated graphics port, and so forth. The system bus 821 may be associated with any suitable bus architecture including, without limitation, an Industry Standard Architecture (ISA), a Micro Channel Architecture (MCA), an Enhanced ISA (EISA), a Video Electronics Standards Association (VESA) architecture, an Accelerated Graphics Port (AGP) architecture, a Peripheral Component Interconnects (PCI) architecture, a PCI-ExpressDocket No. 202410333 architecture, a Personal Computer Memory Card International Association (PCMCIA) architecture, a Universal Serial Bus (USB) architecture, and so forth.

[0031] Continuing with reference to FIG. 4, the computer system 510 may also include a system memory 530 coupled to the system bus 521 for storing information and instructions to be executed by processors 520. The system memory 530 may include computer readable storage media in the form of volatile and / or nonvolatile memory, such as read only memory (ROM) 531 and / or random access memory (RAM) 532. The RAM 532 may include other dynamic storage device(s) (e.g., dynamic RAM, static RAM, and synchronous DRAM). The ROM 531 may include other static storage device(s) (e.g., programmable ROM, erasable PROM, and electrically erasable PROM). In addition, the system memory 530 may be used for storing temporary variables or other intermediate information during the execution of instructions by the processors 520. A basic input / output system 533 (BIOS) containing the basic routines that help to transfer information between elements within computer system 510, such as during start-up, may be stored in the ROM 531 . RAM 532 may contain data and / or program modules that are immediately accessible to and / or presently being operated on by the processors 520. System memory 530 may additionally include, for example, operating system 534, application programs 535, and other program modules 536. Application programs 535 may also include a user portal for development of the application program, allowing input parameters to be entered and modified as necessary.

[0032] The operating system 534 may be loaded into the memory 530 and may provide an interface between other application software executing on the computer system 510 and hardware resources of the computer system 510. More specifically, the operating system 534 may include a set of computer-executable instructions for managing hardware resources of the computer system 510 and for providing common services to other application programs (e.g., managing memory allocation among various application programs). In certain example embodiments, the operating system 534 may control execution of one or more of the program modules depicted as being stored in the data storage 540. The operating system 534 may include any operating system now known or which may be developed in the future including, but not limited to, any server operating system, any mainframe operating system, or any other proprietary or non-proprietary operating system.

[0033] The computer system 510 may also include a disk / media controller 543 coupled to the system bus 521 to control one or more storage devices for storing information and instructions, such as a magnetic hard disk 541 and / or a removable media drive 542 (e.g., floppy disk drive, compact disc drive, tape drive, flash drive, and / or solid state drive). Storage devices 540 may be added to the computer system 510 using an appropriate device interfaceDocket No. 202410333(e.g., a small computer system interface (SCSI), integrated device electronics (IDE), Universal Serial Bus (USB), or FireWire). Storage devices 541 , 542 may be external to the computer system 510.

[0034] The computer system 510 may also include a field device interface 565 coupled to the system bus 521 to control a field device 566, such as a device used in a production line. The computer system 510 may include a user input interface or GUI 561 , which may comprise one or more input devices, such as a keyboard, touchscreen, tablet and / or a pointing device, for interacting with a computer user and providing information to the processors 520.

[0035] The computer system 510 may perform a portion or all of the processing steps of embodiments of the invention in response to the processors 520 executing one or more sequences of one or more instructions contained in a memory, such as the system memory 530. Such instructions may be read into the system memory 530 from another computer readable medium of storage 540, such as the magnetic hard disk 541 or the removable media drive 542. The magnetic hard disk 541 (or solid state drive) and / or removable media drive 542 may contain one or more data stores and data files used by embodiments of the present disclosure. The data store 540 may include, but are not limited to, databases (e.g., relational, object-oriented, etc.), file systems, flat files, distributed data stores in which data is stored on more than one node of a computer network, peer-to-peer network data stores, or the like. The data stores may store various types of data such as, for example, skill data, sensor data, or any other data generated in accordance with the embodiments of the disclosure. Data store contents and data files may be encrypted to improve security. The processors 520 may also be employed in a multi-processing arrangement to execute the one or more sequences of instructions contained in system memory 530. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions. Thus, embodiments are not limited to any specific combination of hardware circuitry and software.

[0036] As stated above, the computer system 510 may include at least one computer readable medium or memory for holding instructions programmed according to embodiments of the invention and for containing data structures, tables, records, or other data described herein. The term “computer readable medium” as used herein refers to any medium that participates in providing instructions to the processors 520 for execution. A computer readable medium may take many forms including, but not limited to, non-transitory, non-volatile media, volatile media, and transmission media. Non-limiting examples of non-volatile media include optical disks, solid state drives, magnetic disks, and magneto-optical disks, such as magnetic hard disk 541 or removable media drive 542. Non-limiting examples of volatile media include dynamic memory, such as system memory 530. Non-limiting examples of transmission mediaDocket No. 202410333 include coaxial cables, copper wire, and fiber optics, including the wires that make up the system bus 521 . Transmission media may also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

[0037] Computer readable medium instructions for carrying out operations of the present disclosure may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, statesetting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present disclosure.

[0038] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, may be implemented by computer readable medium instructions.

[0039] The computing environment 500 may further include the computer system 510 operating in a networked environment using logical connections to one or more remote computers, such as remote computing device 580. The network interface 570 may enable communication, for example, with other remote devices 580 or systems and / or the storage devices 541 , 542 via the network 571 . Remote computing device 580 may be a personal computer (laptop or desktop), a mobile device, a server, a router, a network PC, a peer device or other common network node, and typically includes many or all of the elements described above relative to computer system 510. When used in a networking environment, computerDocket No. 202410333 system 510 may include modem 572 for establishing communications over a network 571 , such as the Internet. Modem 572 may be connected to system bus 521 via user network interface 570, or via another appropriate mechanism.

[0040] Network 571 may be any network or system generally known in the art, including the Internet, an intranet, a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), a direct connection or series of connections, a cellular telephone network, or any other network or medium capable of facilitating communication between computer system 510 and other computers (e.g., remote computing device 580). The network 571 may be wired, wireless or a combination thereof. Wired connections may be implemented using Ethernet, Universal Serial Bus (USB), RJ-6, or any other wired connection generally known in the art. Wireless connections may be implemented using Wi-Fi, WiMAX, and Bluetooth, infrared, cellular networks, satellite or any other wireless connection methodology generally known in the art. Additionally, several networks may work alone or in communication with each other to facilitate communication in the network 571 .

[0041] It should be appreciated that the program modules, applications, computerexecutable instructions, code, or the like depicted in FIG. 4 as being stored in the system memory 530 are merely illustrative and not exhaustive and that processing described as being supported by any particular module may alternatively be distributed across multiple modules or performed by a different module. In addition, various program module(s), script(s), plug-in(s), Application Programming Interface(s) (API(s)), or any other suitable computer-executable code hosted locally on the computer system 510, the remote device 580, and / or hosted on other computing device(s) accessible via one or more of the network(s) 571 , may be provided to support functionality provided by the program modules, applications, or computer-executable code depicted in FIG. 4 and / or additional or alternate functionality. Further, functionality may be modularized differently such that processing described as being supported collectively by the collection of program modules depicted in FIG. 4 may be performed by a fewer or greater number of modules, or functionality described as being supported by any particular module may be supported, at least in part, by another module. In addition, program modules that support the functionality described herein may form part of one or more applications executable across any number of systems or devices in accordance with any suitable computing model such as, for example, a client-server model, a peer-to-peer model, and so forth. In addition, any of the functionality described as being supported by any of the program modules depicted in FIG. 4 may be implemented, at least partially, in hardware and / or firmware across any number of devices.Docket No. 202410333

[0042] It should further be appreciated that the computer system 510 may include alternate and / or additional hardware, software, or firmware components beyond those described or depicted without departing from the scope of the disclosure. More particularly, it should be appreciated that software, firmware, or hardware components depicted as forming part of the computer system 510 are merely illustrative and that some components may not be present or additional components may be provided in various embodiments. While various illustrative program modules have been depicted and described as software modules stored in system memory 530, it should be appreciated that functionality described as being supported by the program modules may be enabled by any combination of hardware, software, and / or firmware. It should further be appreciated that each of the above-mentioned modules may, in various embodiments, represent a logical partitioning of supported functionality. This logical partitioning is depicted for ease of explanation of the functionality and may not be representative of the structure of software, hardware, and / or firmware for implementing the functionality. Accordingly, it should be appreciated that functionality described as being provided by a particular module may, in various embodiments, be provided at least in part by one or more other modules. Further, one or more depicted modules may not be present in certain embodiments, while in other embodiments, additional modules not depicted may be present and may support at least a portion of the described functionality and / or additional functionality. Moreover, while certain modules may be depicted and described as sub-modules of another module, in certain embodiments, such modules may be provided as independent modules or as sub-modules of other modules.

[0043] Although specific embodiments of the disclosure have been described, one of ordinary skill in the art will recognize that numerous other modifications and alternative embodiments are within the scope of the disclosure. For example, any of the functionality and / or processing capabilities described with respect to a particular device or component may be performed by any other device or component. Further, while various illustrative implementations and architectures have been described in accordance with embodiments of the disclosure, one of ordinary skill in the art will appreciate that numerous other modifications to the illustrative implementations and architectures described herein are also within the scope of this disclosure. In addition, it should be appreciated that any operation, element, component, data, or the like described herein as being based on another operation, element, component, data, or the like can be additionally based on one or more other operations, elements, components, data, or the like. Accordingly, the phrase “based on,” or variants thereof, should be interpreted as “based at least in part on.”Docket No. 202410333

[0044] Although embodiments have been described in language specific to structural features and / or methodological acts, it is to be understood that the disclosure is not necessarily limited to the specific features or acts described. Rather, the specific features and acts are disclosed as illustrative forms of implementing the embodiments. Conditional language, such as, among others, “can,” “could,” “might,” or “may,” unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain embodiments could include, while other embodiments do not include, certain features, elements, and / or steps. Thus, such conditional language is not generally intended to imply that features, elements, and / or steps are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without user input or prompting, whether these features, elements, and / or steps are included or are to be performed in any particular embodiment.

[0045] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

Claims

Docket No. 202410333CLAIMSWhat is claimed is:1 . A failure prognostics computer system comprising a degradation evolution model and a parametric model, the computer system further comprising: a sensor configured to capture real samples of data from a physical system, the real samples of data representative of one or more physical quantities of the physical system; a memory storing instructions that, when executed by the processor, cause the processor to: obtain the one or more physical quantities of the physical system; train the parametric model with the one or more physical quantities of the physical system; calibrate the degradation evolution model with one or more calibration parameters that are output from the parametric model; and generate a degradation output from the degradation evolution model that predicts a degradation of the physical system over time.

2. The system as recited in claim 1 , the memory further storing instructions that, when executed by the processor, cause the processor to: based on the degradation output, trigger an action to replace or repair a portion of the physical system.

3. The system as recited in claim 1 , wherein the parametric model defines a first artificial neural network (ANN) configured to generate a latent space representation based on the one or more physical quantities of the physical system.

4. The system as recited in claim 3, wherein the parametric model defines a second ANN coupled to the first ANN, the second ANN configured to generate the one or more calibration parameters based on the latent space representation.

5. The system as recited in claim 4, the memory further storing instructions that, when executed by the processor, cause the processor to: obtain operation condition data representative of one or more operating conditions within the physical system.Docket No. 2024103336. The system as recited in claim 5, the memory further storing instructions that, when executed by the processor, cause the processor to: input the operating condition data and the latent space representation into the second ANN, such that the calibration parameters are based on the operating condition data and latent space representation.

7. The system as recited in any one of the preceding claims, wherein the physical system comprises a bearing component, and the degradation output predicts the degradation of the bearing component due to thermal stress fatigue.

8. A method performed by a failure prognostics computer system that defines a degradation evolution model and a parametric model, the method comprising: obtaining real samples of data from a physical system, the real samples of data representative of one or more physical quantities of the physical system; training the parametric model with the one or more physical quantities of the physical system; calibrating the degradation evolution model with one or more calibration parameters that are output from the parametric model; and generating a degradation output from the degradation evolution model that predicts a degradation of the physical system over time.

9. The method as recited in claim 8, the method further comprising: based on the degradation output, triggering an action to replace or repair a portion of the physical system.

10. The method as recited in claim 8, wherein the parametric model defines a first artificial neural network (ANN), the method further comprising: the first ANN generating a latent space representation based on the one or more physical quantities of the physical system.11 . The method as recited in claim 10, wherein the parametric model further defines a second ANN, the method further comprising: the second ANN generating the one or more calibration parameters based on the latent space representation.Docket No. 20241033312. The method as recited in claim 11 , the method further comprising: obtaining operation condition data representative of one or more operating conditions within the physical system.

13. The method as recited in claim 12, the method further comprising: inputting the operating condition data and the latent space representation into the second ANN, such that the calibration parameters are based on the operating condition data and latent space representation.

14. The method as recited in any one of claims 8 to 13, wherein the physical system comprises a bearing component, the method further comprising: predicting the degradation of the bearing component due to thermal stress fatigue.

15. A non-transitory computer-readable medium encoded with executable instructions that, when executed, cause one or more computer systems to perform a process as in any one of claims 8 to 13.

Images