# US 2021/0240559 A1 · Failure mode specific analytics using parametric models > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2021/0240559 A1 - Document ID: US20210240559A1 - Status: Published application - Kind: A1 - Application number: 17/235,686 - Filed: 2021-04-20 - Published: 2021-08-05 - Earliest claimed: 2019-08-29 - Assignees: Sap SE - Applicants: Sap SE - Inventors: Rashmi B. Shetty - Web page: https://patentgrep.com/patent/US20210240559A1 ## CPC - G06F 11/008: {Reliability or availability analysis} - G06F 11/0751: {Error or fault detection not based on redundancy (power supply failures G06F1/30; network fault management H04L41/06)} - G06F 11/0775: {Content or structure details of the error report, e.g. specific table structure, specific error fields} - G06F 11/079: {Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36)} - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Techniques for predicting failure mode specific reliability characteristics of tangible equipment using parametric probability models are disclosed. In some example embodiments, a computer system receives a model training configuration entered via a user interface, trains a failure curve model for a selected failure mode of a selected equipment model based on the model training configuration at a time indicated by training schedule data, generating, and generates analytical data for the selected failure mode of the selected equipment model using the trained failure curve model. The failure mode corresponds to a specific way in which the equipment model is capable of failing. In some example embodiments, the training of the failure curve model comprises determining a shape parameter and a scale parameter for the failure curve model based on a fitting of failure event data to a continuous probability distribution, and storing the parameters for use in generating the analytical data. ## Claims ### Claim 1 A computer-implemented method performed by a computer system having a memory and at least one hardware processor, the computer-implemented method comprising: generating analytical data for a failure mode of an equipment model using a failure curve model, the failure mode corresponding to a specific way in which the equipment model is capable of failing, the failure curve model being configured to estimate lifetime failure data for the failure mode of the equipment model, the lifetime failure data indicating a probability of the equipment model failing in the specific way of the failure mode at any specific point in time during a lifetime of a physical instance of the equipment model, the analytical data indicating at least a portion of the lifetime failure data for the equipment model corresponding to the failure mode; and causing a visualization of the generated analytical data to be displayed on a computing device. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, wherein the failure mode corresponds to a specific subcomponent of the equipment model. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the generated analytical data comprises probability of failure data. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the generated analytical data comprises remaining useful life data. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the visualization of the generated analytical data comprises a graph indicating corresponding probabilities of failure by the specific way of the failure mode for the lifetime of the physical instance of the equipment model. ### Claim 6 (depends on 1) The computer-implemented method of claim 1, wherein the visualization is generated based on a specific user-selected point on a curve of a graph. ### Claim 7 (depends on 1) The computer-implemented method of claim 1, wherein the failure curve model comprises a parametric model. ### Claim 8 A system comprising: at least one hardware processor; and a non-transitory computer-readable medium storing executable instructions that, when executed, cause the at least one processor to perform operations comprising: generating analytical data for a failure mode of an equipment model using a failure curve model, the failure mode corresponding to a specific way in which the equipment model is capable of failing, the failure curve model being configured to estimate lifetime failure data for the failure mode of the equipment model, the lifetime failure data indicating a probability of the equipment model failing in the specific way of the failure mode at any specific point in time during a lifetime of a physical instance of the equipment model, the analytical data indicating at least a portion of the lifetime failure data for the equipment model corresponding to the failure mode; and causing a visualization of the generated analytical data to be displayed on a computing device. ### Claim 9 (depends on 8) The system of claim 8, wherein the failure mode corresponds to a specific subcomponent of the equipment model. ### Claim 10 (depends on 8) The system of claim 8, wherein the generated analytical data comprises probability of failure data. ### Claim 11 (depends on 8) The system of claim 8, wherein the generated analytical data comprises remaining useful life data. ### Claim 12 (depends on 8) The system of claim 8, wherein the visualization of the generated analytical data comprises a graph indicating corresponding probabilities of failure by the specific way of the failure mode for the lifetime of the physical instance of the equipment model. ### Claim 13 (depends on 8) The system of claim 8, wherein the visualization is generated based on a specific user-selected point on a curve of a graph. ### Claim 14 (depends on 8) The system of claim 8, wherein the failure curve model comprises a parametric model. ### Claim 15 A non-transitory machine-readable storage medium, tangibly embodying a set of instructions that, when executed by at least one hardware processor, causes the at least one processor to perform operations comprising: generating analytical data for a failure mode of an equipment model using a failure curve model, the failure mode corresponding to a specific way in which the equipment model is capable of failing, the failure curve model being configured to estimate lifetime failure data for the failure mode of the equipment model, the lifetime failure data indicating a probability of the equipment model failing in the specific way of the failure mode at any specific point in time during a lifetime of a physical instance of the equipment model, the analytical data indicating at least a portion of the lifetime failure data for the equipment model corresponding to the failure mode; and causing a visualization of the generated analytical data to be displayed on a computing device. ### Claim 16 (depends on 15) The non-transitory machine-readable medium of claim 15, wherein the failure mode corresponds to a specific subcomponent of the equipment model. ### Claim 17 (depends on 15) The non-transitory machine-readable medium of claim 15, wherein the generated analytical data comprises probability of failure data. ### Claim 18 (depends on 15) The non-transitory machine-readable medium of claim 15, wherein the generated analytical data comprises remaining useful life data. ### Claim 19 (depends on 15) The non-transitory machine-readable medium of claim 15, wherein the visualization of the generated analytical data comprises a graph indicating corresponding probabilities of failure by the specific way of the failure mode for the lifetime of the physical instance of the equipment model. ### Claim 20 (depends on 15) The non-transitory machine-readable medium of claim 15, wherein the visualization is generated based on a specific user-selected point on a curve of a graph.